Ruslan Salakhutdinov

NeurIPS Conference 2025 Conference Paper

AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents

• Arman Zharmagambetov
• Chuan Guo
• Ivan Evtimov
• Maya Pavlova
• Ruslan Salakhutdinov
• Kamalika Chaudhuri

Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their users, raising the question of whether they are capable of using it appropriately. In this work, we introduce a new benchmark AgentDAM that measures if AI web-navigation agents follow the privacy principle of "data minimization". For the purposes of our benchmark, data minimization means that the agent uses a piece of potentially sensitive information only if it is "necessary" to complete a particular task. Our benchmark simulates realistic web interaction scenarios end-to-end and is adaptable to all existing web navigation agents. We use AgentDAM to evaluate how well AI agents built on top of GPT-4, Llama-3 and Claude can limit processing of potentially private information, and show that they are prone to inadvertent use of unnecessary sensitive information. We also propose a prompting-based defense that reduces information leakage, and demonstrate that our end-to-end benchmarking provides a more realistic measure than probing LLMs about privacy. Our results highlight that further research is needed to develop AI agents that can prioritize data minimization at inference time. We open source our benchmark at: https: //github. com/facebookresearch/ai-agent-privacy

TMLR Journal 2025 Journal Article

Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation

• Yutong He
• Alexander Robey
• Naoki Murata
• Yiding Jiang
• Joshua Nathaniel Williams
• George J. Pappas
• Hamed Hassani
• Yuki Mitsufuji

Prompt engineering is an effective but labor-intensive way to control text-to-image (T2I) generative models. Its time-intensive nature and complexity have spurred the development of algorithms for automated prompt generation. However, these methods often struggle with transferability across T2I models, require white-box access to the underlying model, or produce non-intuitive prompts. In this work, we introduce PRISM, an algorithm that automatically produces human-interpretable and transferable prompts that can effectively generate desired concepts given only black-box access to T2I models. Inspired by large language model (LLM) jailbreaking, PRISM leverages the in-context learning ability of LLMs to iteratively refine the candidate prompt distribution built upon the reference images. Our experiments demonstrate the versatility and effectiveness of PRISM in generating accurate prompts for objects, styles, and images across multiple T2I models, including Stable Diffusion, DALL-E, and Midjourney.

ICLR Conference 2025 Conference Paper

Dissecting Adversarial Robustness of Multimodal LM Agents

• Chen Henry Wu
• Rishi Rajesh Shah
• Jing Yu Koh
• Ruslan Salakhutdinov
• Daniel Fried
• Aditi Raghunathan

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions, which existing LMs safety evaluations do not adequately address. To bridge this gap, we manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena, a real environment for web agents. To systematically examine the robustness of agents, we propose the Agent Robustness Evaluation (ARE) framework. ARE views the agent as a graph showing the flow of intermediate outputs between components and decomposes robustness as the flow of adversarial information on the graph. We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search. With imperceptible perturbations to a single image (less than 5% of total web page pixels), an attacker can hijack these agents to execute targeted adversarial goals with success rates up to 67%. We also use ARE to rigorously evaluate how the robustness changes as new components are added. We find that inference-time compute that typically improves benign performance can open up new vulnerabilities and harm robustness. An attacker can compromise the evaluator used by the reflexion agent and the value function of the tree search agent, which increases the attack success relatively by 15% and 20%. Our data and code for attacks, defenses, and evaluation are at https://github.com/ChenWu98/agent-attack

ICRA Conference 2025 Conference Paper

Local Policies Enable Zero-Shot Long-Horizon Manipulation

• Murtaza Dalal
• Min Liu
• Walter Talbott
• Chen Chen 0032
• Deepak Pathak
• Jian Zhang 0050
• Ruslan Salakhutdinov

Sim2real for robotic manipulation is difficult due to the challenges of simulating complex contacts and generating realistic task distributions. To tackle the latter problem, we introduce ManipGen, which leverages a new class of policies for sim2real transfer: local policies. Locality enables a variety of appealing properties including invariances to absolute robot and object pose, skill ordering, and global scene configuration. We combine these policies with foundation models for vision, language and motion planning and demonstrate SOTA zero-shot performance of our method to Robosuite benchmark tasks in simulation (97 %). We transfer our local policies from simulation to reality and observe they can solve unseen long-horizon manipulation tasks with up to 8 stages with significant pose, object and scene configuration variation. ManipGen outperforms SOTA approaches such as SayCan, Open VLA, LLMTrajGen and VoxPoser across 50 real-world manipulation tasks by 36%, 76%, 62% and 60% respectively. Video results at mihdalal.github.io/manipgen

IROS Conference 2025 Conference Paper

Neural MP: A Neural Motion Planner

• Murtaza Dalal
• Jiahui Yang
• Russell Mendonca
• Youssef Khaky
• Ruslan Salakhutdinov
• Deepak Pathak

The current paradigm for motion planning generates solutions from scratch for every new problem, which consumes significant amounts of time and computational resources. For complex, cluttered scenes, motion planning approaches can often take minutes to produce a solution, while humans are able to accurately and safely reach any goal in seconds by leveraging their prior experience. We seek to do the same by applying data-driven learning at scale to the problem of motion planning. Our approach builds a large number of complex scenes in simulation, collects expert data from a motion planner, then distills it into a reactive neural policy. We then combine this with lightweight optimization to obtain a safe path for real world deployment. We perform a thorough evaluation of our method on 64 motion planning tasks across four diverse environments with randomized poses, scenes and obstacles, in the real world, demonstrating an improvement of 23%, 17% and 79% motion planning success rate over state of the art sampling, optimization and learning based planning methods. All code, models and datasets will be released on acceptance. Video results available at mihdalal.github.io/neuralmotionplanner.

ICML Conference 2025 Conference Paper

Optimizing Test-Time Compute via Meta Reinforcement Finetuning

• Yuxiao Qu
• Matthew Y. R. Yang
• Amrith Setlur
• Lewis Tunstall
• Edward Emanuel Beeching
• Ruslan Salakhutdinov
• Aviral Kumar

Training models to efficiently use test-time compute is crucial for improving the reasoning performance of LLMs. While current methods mostly do so via fine-tuning on search traces or running RL against the 0/1 outcome reward, do these approaches efficiently utilize test-time compute? Would these approaches continue to scale as the budget improves? In this paper, we try to answer these questions. We formalize the problem of optimizing test-time compute as a meta reinforcement learning (RL) problem, which provides a principled perspective on spending test-time compute from the lens of exploration and exploitation. It also motivates the use of cumulative regret to measure the efficacy of test-time compute by viewing a long output stream as consisting of several episodes from the model. While current state-of-the-art models do not optimize regret, we show that regret can be minimized by running final 0/1 reward RL regularized by a dense reward bonus, given by the "information gain" from each subsequent block in the output stream. We prescribe an approach for quantifying information gain, which measures the utility of an intermediate segment of tokens towards improving accuracy of the final answer. We instantiate this idea to develop MRT, a new class of finetuning methods for optimizing test-time compute. Fine-tuning with MRT leads to substantial improvements in both performance and token efficiency on the AIME dataset.

NeurIPS Conference 2025 Conference Paper

Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models

• Wen-Tse Chen
• Jiayu Chen
• Fahim Tajwar
• Hao Zhu
• Xintong Duan
• Ruslan Salakhutdinov
• Jeff Schneider

Learning from self-sampled data and sparse environmental feedback remains a fundamental challenge in training self-evolving agents. Temporal credit assignment mitigates this issue by transforming sparse feedback into dense supervision signals. However, previous approaches typically depend on domain-specific value functions for credit assignment, which suffer from poor sample efficiency and limited generalization. In this work, we propose to leverage pre-trained knowledge from large language models (LLMs) to transform sparse rewards into dense training signals (i. e. , the advantage function) through retrospective in-context learning (RICL). We further propose an online learning framework, RICOL, which iteratively refines the policy based on the credit assignment results from RICL. We empirically demonstrate that RICL can accurately estimate the advantage function with limited samples and effectively identify critical states for temporal credit assignment. Extended evaluation on the BabyAI benchmark shows that RICOL significantly improves sample efficiency compared to traditional online RL algorithms while achieving performance comparable to imitation learning from expert demonstartions. Our findings highlight the potential of leveraging LLMs for temporal credit assignment, paving the way for more sample-efficient and generalizable RL paradigms.

ICLR Conference 2025 Conference Paper

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models

• Ce Zhang 0009
• Zifu Wan
• Zhehan Kan
• Martin Q. Ma
• Simon Stepputtis
• Deva Ramanan
• Ruslan Salakhutdinov
• Louis-Philippe Morency

While recent Large Vision-Language Models (LVLMs) have shown remarkable performance in multi-modal tasks, they are prone to generating hallucinatory text responses that do not align with the given visual input, which restricts their practical applicability in real-world scenarios. In this work, inspired by the observation that the text-to-image generation process is the inverse of image-conditioned response generation in LVLMs, we explore the potential of leveraging text-to-image generative models to assist in mitigating hallucinations in LVLMs. We discover that generative models can offer valuable self-feedback for mitigating hallucinations at both the response and token levels. Building on this insight, we introduce self-correcting Decoding with Generative Feedback (DeGF), a novel training-free algorithm that incorporates feedback from text-to-image generative models into the decoding process to effectively mitigate hallucinations in LVLMs. Specifically, DeGF generates an image from the initial response produced by LVLMs, which acts as an auxiliary visual reference and provides self-feedback to verify and correct the initial response through complementary or contrastive decoding. Extensive experimental results validate the effectiveness of our approach in mitigating diverse types of hallucinations, consistently surpassing state-of-the-art methods across six benchmarks. Code is available at https://github.com/zhangce01/DeGF.

TMLR Journal 2025 Journal Article

State Combinatorial Generalization In Decision Making With Conditional Diffusion Models

• Xintong Duan
• Yutong He
• Fahim Tajwar
• Wentse Chen
• Ruslan Salakhutdinov
• Jeff Schneider

Many real-world decision-making problems are combinatorial in nature, where states (e.g., surrounding traffic of a self-driving car) can be seen as a combination of basic elements (e.g., pedestrians, trees, and other cars). Due to combinatorial complexity, observing all combinations of basic elements in the training set is infeasible, which leads to an essential yet understudied problem of zero-shot generalization to states that are unseen combinations of previously seen elements. In this work, we first formalize this problem and then demonstrate how existing value-based reinforcement learning (RL) algorithms struggle due to unreliable value predictions in unseen states. We argue that this problem cannot be addressed with exploration alone, but requires more expressive and generalizable models. We demonstrate that behavior cloning with a conditioned diffusion model trained on successful trajectory generalizes better to states formed by new combinations of seen elements than traditional RL methods. Through experiments in maze, driving, and multiagent environments, we show that conditioned diffusion models outperform traditional RL techniques and highlight the broad applicability of our problem formulation.

ICML Conference 2025 Conference Paper

Training a Generally Curious Agent

• Fahim Tajwar
• Yiding Jiang
• Abitha Thankaraj
• Sumaita Sadia Rahman
• J. Zico Kolter
• Jeff G. Schneider
• Ruslan Salakhutdinov

Efficient exploration is essential for intelligent systems interacting with their environment, but existing language models often fall short in scenarios that require strategic information gathering. In this paper, we present Paprika, a fine-tuning approach that enables language models to develop general decision-making capabilities that are not confined to particular environments. By training on synthetic interaction data from different tasks that require diverse strategies, Paprika teaches models to explore and adapt their behavior on a new task based on environment feedback in-context without more gradient updates. Experimental results show that models fine-tuned with Paprika can effectively transfer their learned decision-making capabilities to entirely unseen tasks without additional training. Unlike traditional training, our approach’s primary bottleneck lies in sampling useful interaction data instead of model updates. To improve sample efficiency, we propose a curriculum learning strategy that prioritizes sampling trajectories from tasks with high learning potential. These results suggest a promising path towards AI systems that can autonomously solve novel sequential decision-making problems that require interactions with the external world.

TMLR Journal 2025 Journal Article

Tree Search for Language Model Agents

• Jing Yu Koh
• Stephen Marcus McAleer
• Daniel Fried
• Ruslan Salakhutdinov

Autonomous agents powered by language models (LMs) have demonstrated promise in their ability to perform decision-making tasks such as web automation. However, a key limitation remains: LMs, primarily optimized for natural language understanding and generation, struggle with multi-step reasoning, planning, and using environmental feedback when attempting to solve realistic computer tasks. Towards addressing this, we propose an inference-time search algorithm for LM agents to explicitly perform exploration and multi-step planning in interactive web environments. Our approach is a form of best-first tree search that operates within the actual environment space, and is complementary with most existing state-of-the-art agents. It is the first tree search algorithm for LM agents that shows effectiveness on realistic web tasks. On the challenging VisualWebArena benchmark, applying our search algorithm on top of a GPT-4o agent yields a 39.7% relative increase in success rate compared to the same baseline without search, setting a state-of-the-art success rate of 26.4%. On WebArena, search also yields a 28.0% relative improvement over a baseline agent, setting a competitive success rate of 19.2%. Our experiments showcase the effectiveness of search for web agents, and we demonstrate that performance scales with increased test-time compute.

ICLR Conference 2025 Conference Paper

Wayward Concepts In Multimodal Models

• Brandon Trabucco
• Max Gurinas
• Kyle Doherty
• Ruslan Salakhutdinov

Large multimodal models such as Stable Diffusion can generate, detect, and classify new visual concepts after optimizing just the prompt. How are prompt embeddings for visual concepts found by prompt tuning methods different from typical discrete prompts? We conduct a large-scale analysis on three state-of-the-art models in text-to-image generation, open-set object detection, and zero-shot classification, and find that prompts optimized to represent new visual concepts are akin to an adversarial attack on the text encoder. Across 4,800 new embeddings trained for 40 diverse visual concepts on four standard datasets, we find perturbations within an $\epsilon$-ball to any prompt that reprogram models to generate, detect, and classify arbitrary subjects. These perturbations target the final-layers in text encoders, and steer pooling tokens towards the subject. We explore the transferability of these prompts, and find that perturbations reprogramming multimodal models are initialization-specific, and model-specific. Code for reproducing our work is available at the following site: https://wayward-concepts.github.io.

ICLR Conference 2024 Conference Paper

Confronting Reward Model Overoptimization with Constrained RLHF

• Ted Moskovitz
• Aaditya K. Singh
• DJ Strouse
• Tuomas Sandholm
• Ruslan Salakhutdinov
• Anca D. Dragan
• Stephen Marcus McAleer

Large language models are typically aligned with human preferences by optimizing reward models (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a composition of simpler reward models which each capture a different aspect of language quality. This itself presents a challenge, as it is difficult to appropriately weight these component RMs when combining them. Compounding this difficulty, because any RM is only a proxy for human evaluation, this process is vulnerable to *overoptimization*, wherein past a certain point, accumulating higher reward is associated with worse human ratings. In this paper, we perform the first study on overoptimization in composite RMs, showing that correlation between component RMs has a significant effect on the locations of these points. We then introduce an approach to solve this issue using constrained reinforcement learning as a means of preventing the agent from exceeding each RM's threshold of usefulness. Our method addresses the problem of weighting component RMs by learning dynamic weights, naturally given by the Lagrange multipliers. As a result, each RM stays within the range at which it is an effective proxy, improving evaluation performance. Finally, we introduce an adaptive method using gradient-free optimization to identify and optimize towards these points during a single run.

ICLR Conference 2024 Conference Paper

Contrastive Difference Predictive Coding

• Chongyi Zheng
• Ruslan Salakhutdinov
• Benjamin Eysenbach

Predicting and reasoning about the future lie at the heart of many time-series questions. For example, goal-conditioned reinforcement learning can be viewed as learning representations to predict which states are likely to be visited in the future. While prior methods have used contrastive predictive coding to model time series data, learning representations that encode long-term dependencies usually requires large amounts of data. In this paper, we introduce a temporal difference version of contrastive predictive coding that stitches together pieces of different time series data to decrease the amount of data required to learn predictions of future events. We apply this representation learning method to derive an off-policy algorithm for goal-conditioned RL. Experiments demonstrate that, compared with prior RL methods, ours achieves $2 \times$ median improvement in success rates and can better cope with stochastic environments. In tabular settings, we show that our method is about $20\times$ more sample efficient than the successor representation and $1500 \times$ more sample efficient than the standard (Monte Carlo) version of contrastive predictive coding.

ICLR Conference 2024 Conference Paper

Effective Data Augmentation With Diffusion Models

• Brandon Trabucco
• Kyle Doherty
• Max Gurinas
• Ruslan Salakhutdinov

Data augmentation is one of the most prevalent tools in deep learning, underpinning many recent advances, including those from classification, generative models, and representation learning. The standard approach to data augmentation combines simple transformations like rotations and flips to generate new images from existing ones. However, these new images lack diversity along key semantic axes present in the data. Current augmentations cannot alter the high-level semantic attributes, such as animal species present in a scene, to enhance the diversity of data. We address the lack of diversity in data augmentation with image-to-image transformations parameterized by pre-trained text-to-image diffusion models. Our method edits images to change their semantics using an off-the-shelf diffusion model, and generalizes to novel visual concepts from a few labelled examples. We evaluate our approach on few-shot image classification tasks, and on a real-world weed recognition task, and observe an improvement in accuracy in tested domains.

NeurIPS Conference 2024 Conference Paper

HEMM: Holistic Evaluation of Multimodal Foundation Models

• Paul Pu Liang
• Akshay Goindani
• Talha Chafekar
• Leena Mathur
• Haofei Yu
• Ruslan Salakhutdinov
• Louis-Philippe Morency

Multimodal foundation models that can holistically process text alongside images, video, audio, and other sensory modalities are increasingly used in a variety of real-world applications. However, it is challenging to characterize and study progress in multimodal foundation models, given the range of possible modeling decisions, tasks, and domains. In this paper, we introduce Holistic Evaluation of Multimodal Models (HEMM) to systematically evaluate the capabilities of multimodal foundation models across a set of 3 dimensions: basic skills, information flow, and real-world use cases. Basic multimodal skills are internal abilities required to solve problems, such as learning interactions across modalities, fine-grained alignment, multi-step reasoning, and the ability to handle external knowledge. Information flow studies how multimodal content changes during a task through querying, translation, editing, and fusion. Use cases span domain-specific challenges introduced in real-world multimedia, affective computing, natural sciences, healthcare, and human-computer interaction applications. Through comprehensive experiments across the 30 tasks in HEMM, we (1) identify key dataset dimensions (e. g. , basic skills, information flows, and use cases) that pose challenges to today’s models, and (2) distill performance trends regarding how different modeling dimensions (e. g. , scale, pre-training data, multimodal alignment, pre-training, and instruction tuning objectives) influence performance. Our conclusions regarding challenging multimodal interactions, use cases, and tasks requiring reasoning and external knowledge, the benefits of data and model scale, and the impacts of instruction-tuning yield actionable insights for future work in multimodal foundation models.

NeurIPS Conference 2024 Conference Paper

Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference

• Benjamin Eysenbach
• Vivek Myers
• Ruslan Salakhutdinov
• Sergey Levine

Given time series data, how can we answer questions like what will happen in the future? '' and how did we get here? '' These sorts of probabilistic inference questions are challenging when observations are high-dimensional. In this paper, we show how these questions can have compact, closed form solutions in terms of learned representations. The key idea is to apply a variant of contrastive learning to time series data. Prior work already shows that the representations learned by contrastive learning encode a probability ratio. By extending prior work to show that the marginal distribution over representations is Gaussian, we can then prove that joint distribution of representations is also Gaussian. Taken together, these results show that representations learned via temporal contrastive learning follow a Gauss-Markov chain, a graphical model where inference (e. g. , prediction, planning) over representations corresponds to inverting a low-dimensional matrix. In one special case, inferring intermediate representations will be equivalent to interpolating between the learned representations. We validate our theory using numerical simulations on tasks up to 46-dimensions.

ICLR Conference 2024 Conference Paper

Manifold Preserving Guided Diffusion

• Yutong He
• Naoki Murata
• Chieh-Hsin Lai
• Yuhta Takida
• Toshimitsu Uesaka
• Dongjun Kim
• Wei-Hsiang Liao 0001
• Yuki Mitsufuji

Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. In this paper, we propose Manifold Preserving Guided Diffusion (MPGD), a training-free conditional generation framework that leverages pretrained diffusion models and off-the-shelf neural networks with minimal additional inference cost for a broad range of tasks. Specifically, we leverage the manifold hypothesis to refine the guided diffusion steps and introduce a shortcut algorithm in the process. We then propose two methods for on-manifold training-free guidance using pre-trained autoencoders and demonstrate that our shortcut inherently preserves the manifolds when applied to latent diffusion models. Our experiments show that MPGD is efficient and effective for solving a variety of conditional generation applications in low-compute settings, and can consistently offer up to 3.8× speed-ups with the same number of diffusion steps while maintaining high sample quality compared to the baselines.

ICLR Conference 2024 Conference Paper

Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications

• Paul Pu Liang
• Chun Kai Ling
• Yun Cheng
• Alexander Obolenskiy
• Yudong Liu
• Rohan Pandey
• Alex Wilf
• Louis-Philippe Morency

In many machine learning systems that jointly learn from multiple modalities, a core research question is to understand the nature of multimodal interactions: how modalities combine to provide new task-relevant information that was not present in either alone. We study this challenge of interaction quantification in a semi-supervised setting with only labeled unimodal data and naturally co-occurring multimodal data (e.g., unlabeled images and captions, video and corresponding audio) but when labeling them is time-consuming. Using a precise information-theoretic definition of interactions, our key contribution is the derivation of lower and upper bounds to quantify the amount of multimodal interactions in this semi-supervised setting. We propose two lower bounds: one based on the shared information between modalities and the other based on disagreement between separately trained unimodal classifiers, and derive an upper bound through connections to approximate algorithms for min-entropy couplings. We validate these estimated bounds and show how they accurately track true interactions. Finally, we show how these theoretical results can be used to estimate multimodal model performance, guide data collection, and select appropriate multimodal models for various tasks.

ICLR Conference 2024 Conference Paper

Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks

• Murtaza Dalal
• Tarun Chiruvolu
• Devendra Singh Chaplot
• Ruslan Salakhutdinov

Large Language Models (LLMs) are highly capable of performing planning for long-horizon robotics tasks, yet existing methods require access to a pre-defined skill library (*e.g.* picking, placing, pulling, pushing, navigating). However, LLM planning does not address how to design or learn those behaviors, which remains challenging particularly in long-horizon settings. Furthermore, for many tasks of interest, the robot needs to be able to adjust its behavior in a fine-grained manner, requiring the agent to be capable of modifying *low-level* control actions. Can we instead use the internet-scale knowledge from LLMs for high-level policies, guiding reinforcement learning (RL) policies to efficiently solve robotic control tasks online without requiring a pre-determined set of skills? In this paper, we propose **Plan-Seq-Learn** (PSL): a modular approach that uses motion planning to bridge the gap between abstract language and learned low-level control for solving long-horizon robotics tasks from scratch. We demonstrate that PSL is capable of solving 20+ challenging single and multi-stage robotics tasks on four benchmarks at success rates of over 80% from raw visual input, out-performing language-based, classical, and end-to-end approaches. Video results and code at https://planseqlearn.github.io/

ICLR Conference 2024 Conference Paper

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data

• Chongyi Zheng
• Benjamin Eysenbach
• Homer Rich Walke
• Patrick Yin
• Kuan Fang
• Ruslan Salakhutdinov
• Sergey Levine

Robotic systems that rely primarily on self-supervised learning have the potential to decrease the amount of human annotation and engineering effort required to learn control strategies. In the same way that prior robotic systems have leveraged self-supervised techniques from computer vision (CV) and natural language processing (NLP), our work builds on prior work showing that the reinforcement learning (RL) itself can be cast as a self-supervised problem: learning to reach any goal without human-specified rewards or labels. Despite the seeming appeal, little (if any) prior work has demonstrated how self-supervised RL methods can be practically deployed on robotic systems. By first studying a challenging simulated version of this task, we discover design decisions about architectures and hyperparameters that increase the success rate by $2 \times$. These findings lay the groundwork for our main result: we demonstrate that a self-supervised RL algorithm based on contrastive learning can solve real-world, image-based robotic manipulation tasks, with tasks being specified by a single goal image provided after training.

NeurIPS Conference 2024 Conference Paper

Stylus: Automatic Adapter Selection for Diffusion Models

• Michael Luo
• Justin Wong
• Brandon Trabucco
• Yanping Huang
• Joseph E. Gonzalez
• Zhifeng Chen
• Ruslan Salakhutdinov
• Ion Stoica

Beyond scaling base models with more data or parameters, fine-tuned adapters provide an alternative way to generate high fidelity, custom images at reduced costs. As such, adapters have been widely adopted by open-source communities, accumulating a database of over 100K adapters—most of which are highly customized with insufficient descriptions. To generate high quality images, this paper explores the problem of matching the prompt to a Stylus of relevant adapters, built on recent work that highlight the performance gains of composing adapters. We introduce Stylus, which efficiently selects and automatically composes task-specific adapters based on a prompt's keywords. Stylus outlines a three-stage approach that first summarizes adapters with improved descriptions and embeddings, retrieves relevant adapters, and then further assembles adapters based on prompts' keywords by checking how well they fit the prompt. To evaluate Stylus, we developed StylusDocs, a curated dataset featuring 75K adapters with pre-computed adapter embeddings. In our evaluation on popular Stable Diffusion checkpoints, Stylus achieves greater CLIP/FID Pareto efficiency and is twice as preferred, with humans and multimodal models as evaluators, over the base model.

ICML Conference 2023 Conference Paper

A Connection between One-Step RL and Critic Regularization in Reinforcement Learning

• Benjamin Eysenbach
• Matthieu Geist
• Sergey Levine
• Ruslan Salakhutdinov

As with any machine learning problem with limited data, effective offline RL algorithms require careful regularization to avoid overfitting. One class of methods, known as one-step RL, perform just one step of policy improvement. These methods, which include advantage-weighted regression and conditional behavioral cloning, are thus simple and stable, but can have limited asymptotic performance. A second class of methods, known as critic regularization, perform many steps of policy improvement with a regularized objective. These methods typically require more compute but have appealing lower-bound guarantees. In this paper, we draw a connection between these methods: applying a multi-step critic regularization method with a regularization coefficient of 1 yields the same policy as one-step RL. While our theoretical results require assumptions (e. g. , deterministic dynamics), our experiments nevertheless show that our analysis makes accurate, testable predictions about practical offline RL methods (CQL and one-step RL) with commonly-used hyperparameters.

ICLR Conference 2023 Conference Paper

A Simple Approach for Visual Room Rearrangement: 3D Mapping and Semantic Search

• Brandon Trabucco
• Gunnar A. Sigurdsson
• Robinson Piramuthu
• Gaurav S. Sukhatme
• Ruslan Salakhutdinov

Physically rearranging objects is an important capability for embodied agents. Visual room rearrangement evaluates an agent's ability to rearrange objects in a room to a desired goal based solely on visual input. We propose a simple yet effective method for this problem: (1) search for and map which objects need to be rearranged, and (2) rearrange each object until the task is complete. Our approach consists of an off-the-shelf semantic segmentation model, voxel-based semantic map, and semantic search policy to efficiently find objects that need to be rearranged. Our method was the winning submission to the AI2-THOR Rearrangement Challenge in the 2022 Embodied AI Workshop at CVPR 2022, and improves on current state-of-the-art end-to-end reinforcement learning-based methods that learn visual room rearrangement policies from 0.53% correct rearrangement to 16.56%, using only 2.7% as many samples from the environment.

NeurIPS Conference 2023 Conference Paper

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

• Paul Pu Liang
• Zihao Deng
• Martin Q. Ma
• James Y. Zou
• Louis-Philippe Morency
• Ruslan Salakhutdinov

In a wide range of multimodal tasks, contrastive learning has become a particularly appealing approach since it can successfully learn representations from abundant unlabeled data with only pairing information (e. g. , image-caption or video-audio pairs). Underpinning these approaches is the assumption of multi-view redundancy - that shared information between modalities is necessary and sufficient for downstream tasks. However, in many real-world settings, task-relevant information is also contained in modality-unique regions: information that is only present in one modality but still relevant to the task. How can we learn self-supervised multimodal representations to capture both shared and unique information relevant to downstream tasks? This paper proposes FactorCL, a new multimodal representation learning method to go beyond multi-view redundancy. FactorCL is built from three new contributions: (1) factorizing task-relevant information into shared and unique representations, (2) capturing task-relevant information via maximizing MI lower bounds and removing task-irrelevant information via minimizing MI upper bounds, and (3) multimodal data augmentations to approximate task relevance without labels. On large-scale real-world datasets, FactorCL captures both shared and unique information and achieves state-of-the-art results on six benchmarks.

ICML Conference 2023 Conference Paper

Graph Generative Model for Benchmarking Graph Neural Networks

• Minji Yoon
• Yue Wu 0001
• John Palowitch
• Bryan Perozzi
• Ruslan Salakhutdinov

As the field of Graph Neural Networks (GNN) continues to grow, it experiences a corresponding increase in the need for large, real-world datasets to train and test new GNN models on challenging, realistic problems. Unfortunately, such graph datasets are often generated from online, highly privacy-restricted ecosystems, which makes research and development on these datasets hard, if not impossible. This greatly reduces the amount of benchmark graphs available to researchers, causing the field to rely only on a handful of publicly-available datasets. To address this problem, we introduce a novel graph generative model, Computation Graph Transformer (CGT) that learns and reproduces the distribution of real-world graphs in a privacy-controlled way. More specifically, CGT (1) generates effective benchmark graphs on which GNNs show similar task performance as on the source graphs, (2) scales to process large-scale graphs, (3) incorporates off-the-shelf privacy modules to guarantee end-user privacy of the generated graph. Extensive experiments across a vast body of graph generative models show that only our model can successfully generate privacy-controlled, synthetic substitutes of large-scale real-world graphs that can be effectively used to benchmark GNN models.

ICML Conference 2023 Conference Paper

Grounding Language Models to Images for Multimodal Inputs and Outputs

• Jing Yu Koh
• Ruslan Salakhutdinov
• Daniel Fried

We propose an efficient method to ground pretrained text-only language models to the visual domain, enabling them to process arbitrarily interleaved image-and-text data, and generate text interleaved with retrieved images. Our method leverages the abilities of language models learnt from large scale text-only pretraining, such as in-context learning and free-form text generation. We keep the language model frozen, and finetune input and output linear layers to enable cross-modality interactions. This allows our model to process arbitrarily interleaved image-and-text inputs, and generate free-form text interleaved with retrieved images. We achieve strong zero-shot performance on grounded tasks such as contextual image retrieval and multimodal dialogue, and showcase compelling interactive abilities. Our approach works with any off-the-shelf language model and paves the way towards an effective, general solution for leveraging pretrained language models in visually grounded settings.

ICLR Conference 2023 Conference Paper

MultiViz: Towards Visualizing and Understanding Multimodal Models

• Paul Pu Liang
• Yiwei Lyu 0001
• Gunjan Chhablani
• Nihal Jain
• Zihao Deng
• Xingbo Wang 0001
• Louis-Philippe Morency
• Ruslan Salakhutdinov

The promise of multimodal models for real-world applications has inspired research in visualizing and understanding their internal mechanics with the end goal of empowering stakeholders to visualize model behavior, perform model debugging, and promote trust in machine learning models. However, modern multimodal models are typically black-box neural networks, which makes it challenging to understand their internal mechanics. How can we visualize the internal modeling of multimodal interactions in these models? Our paper aims to fill this gap by proposing MultiViz, a method for analyzing the behavior of multimodal models by scaffolding the problem of interpretability into 4 stages: (1) unimodal importance: how each modality contributes towards downstream modeling and prediction, (2) cross-modal interactions: how different modalities relate with each other, (3) multimodal representations: how unimodal and cross-modal interactions are represented in decision-level features, and (4) multimodal prediction: how decision-level features are composed to make a prediction. MultiViz is designed to operate on diverse modalities, models, tasks, and research areas. Through experiments on 8 trained models across 6 real-world tasks, we show that the complementary stages in MultiViz together enable users to (1) simulate model predictions, (2) assign interpretable concepts to features, (3) perform error analysis on model misclassifications, and (4) use insights from error analysis to debug models. MultiViz is publicly available, will be regularly updated with new interpretation tools and metrics, and welcomes inputs from the community.

JMLR Journal 2023 Journal Article

MultiZoo and MultiBench: A Standardized Toolkit for Multimodal Deep Learning

• Paul Pu Liang
• Yiwei Lyu
• Xiang Fan
• Arav Agarwal
• Yun Cheng
• Louis-Philippe Morency
• Ruslan Salakhutdinov

Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. In order to accelerate progress towards understudied modalities and tasks while ensuring real-world robustness, we release MultiZoo, a public toolkit consisting of standardized implementations of >20 core multimodal algorithms and MultiBench, a large-scale benchmark spanning 15 datasets, 10 modalities, 20 prediction tasks, and 6 research areas. Together, these provide an automated end-to-end machine learning pipeline that simplifies and standardizes data loading, experimental setup, and model evaluation. To enable holistic evaluation, we offer a comprehensive methodology to assess (1) generalization, (2) time and space complexity, and (3) modality robustness. MultiBench paves the way towards a better understanding of the capabilities and limitations of multimodal models, while ensuring ease of use, accessibility, and reproducibility. Our toolkits are publicly available, will be regularly updated, and welcome inputs from the community. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2023. ( edit, beta )

TMLR Journal 2023 Journal Article

Probing Predictions on OOD Images via Nearest Categories

• Yao-Yuan Yang
• Cyrus Rashtchian
• Ruslan Salakhutdinov
• Kamalika Chaudhuri

We study out-of-distribution (OOD) prediction behavior of neural networks when they classify images from unseen classes or corrupted images. To probe the OOD behavior, we introduce a new measure, nearest category generalization (NCG), where we compute the fraction of OOD inputs that are classified with the same label as their nearest neighbor in the training set. Our motivation stems from understanding the prediction patterns of adversarially robust networks, since previous work has identified unexpected consequences of training to be robust to norm-bounded perturbations. We find that robust networks have consistently higher NCG accuracy than natural training, even when the OOD data is much farther away than the robustness radius. This implies that the local regularization of robust training has a significant impact on the network’s decision regions. We replicate our findings using many datasets, comparing new and existing training methods. Overall, adversarially robust networks resemble a nearest neighbor classifier when it comes to OOD data.

ICLR Conference 2023 Conference Paper

Scenario-based Question Answering with Interacting Contextual Properties

• Haitian Sun
• William W. Cohen
• Ruslan Salakhutdinov

In the scenario-based Question Answering (QA) task, models are asked to find answers that are appropriate to the user scenarios associated with the question and identify information that is missing from the scenarios but is necessary for the answers to hold. Scenarios commonly include multiple properties of users, such as age, employment status, and income level for the question “How much can I claim from this benefit”. The properties relevant to a potential answer are given in a document, which will state conditions necessary for the answer to hold. Documents also may specify how conditions interact with each other, e.g. with text like “one of the conditions below must apply”. Although understanding the relationship between conditions is crucial for solving this challenging QA task, limited work has been done so far in modeling this. In this paper, we propose the T-Reasoner model, which solves this problem with three jointly learned modules: an entailment module which checks whether a condition has been satisfied by the scenario, a decoding module which locates eligible answers from documents, and a reasoning module which infers the relationship between conditions and performs a reasoning step to determine the logically consistent answers and identify missing conditions. T-Reasoner outperforms strong baselines on a synthetic scenario-based QA dataset and achieves a new state-of-the-art on two scenario-based QA benchmarks, outperforming the prior best models by 3-10 points.

IROS Conference 2023 Conference Paper

Self-Supervised Object Goal Navigation with In-Situ Finetuning

• So Yeon Min
• Yao-Hung Hubert Tsai
• Wei Ding
• Ali Farhadi
• Ruslan Salakhutdinov
• Yonatan Bisk
• Jian Zhang 0050

A household robot should be able to navigate to target objects without requiring users to first annotate everything in their home. Most current approaches to object navigation do not test on real robots and rely solely on reconstructed scans of houses and their expensively labeled semantic 3D meshes. In this work, our goal is to build an agent that builds self-supervised models of the world via exploration, the same as a child might - thus we (1) eschew the expense of labeled 3D mesh and (2) enable self-supervised in-situ finetuning in the real world. We identify a strong source of self-supervision (Location Consistency - LocCon) that can train all components of an ObjectNav agent, using unannotated simulated houses. Our key insight is that embodied agents can leverage location consistency as a self-supervision signal - collecting images from different views/angles and applying contrastive learning. We show that our agent can perform competitively in the real world and simulation. Our results also indicate that supervised training with 3D mesh annotations causes models to learn simulation artifacts, which are not transferrable to the real world. In contrast, our LocCon shows the most robust transfer in the real world among the set of models we compare to, and that the real-world performance of all models can be further improved with self-supervised LocCon in-situ training.

ICLR Conference 2023 Conference Paper

Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective

• Raj Ghugare
• Homanga Bharadhwaj
• Benjamin Eysenbach
• Sergey Levine
• Ruslan Salakhutdinov

While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learning to model raw observations from high dimensional sensors can be challenging. Prior work has addressed this challenge by learning low-dimensional representation of observations through auxiliary objectives, such as reconstruction or value prediction. However, the alignment between these auxiliary objectives and the RL objective is often unclear. In this work, we propose a single objective which jointly optimizes a latent-space model and policy to achieve high returns while remaining self-consistent. This objective is a lower bound on expected returns. Unlike prior bounds for model-based RL on policy exploration or model guarantees, our bound is directly on the overall RL objective. We demonstrate that the resulting algorithm matches or improves the sample-efficiency of the best prior model-based and model-free RL methods. While sample efficient methods typically are computationally demanding, our method attains the performance of SAC in about 50\% less wall-clock time.

ICLR Conference 2022 Conference Paper

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks

• Tianjun Zhang
• Benjamin Eysenbach
• Ruslan Salakhutdinov
• Sergey Levine
• Joseph E. Gonzalez

Goal-conditioned reinforcement learning (RL) has shown great success recently at solving a wide range of tasks(e.g., navigation, robotic manipulation). However, learning to reach distant goals remains a central challenge to the field, and the task is particularly hard without any offline data, expert demonstrations, and reward shaping. In this paper, we propose to solve the distant goal-reaching task by using search at training time to generate a curriculum of intermediate states. Specifically, we introduce the algorithm Classifier-Planning (C-Planning) by framing the learning of the goal-conditioned policies as variational inference. C-Planning naturally follows expectation maximization (EM): the E-step corresponds to planning an optimal sequence of waypoints using graph search, while the M-step aims to learn a goal-conditioned policy to reach those waypoints. One essential difficulty of designing such an algorithm is accurately modeling the distribution over way-points to sample from. In C-Planning, we propose to sample the waypoints using contrastive methods to learn a value function. Unlike prior methods that combine goal-conditioned RL with graph search, ours performs search only during training and not testing, significantly decreasing the compute costs of deploying the learned policy. Empirically, we demonstrate that our method not only improves the sample efficiency of prior methods but also successfully solves temporally extended navigation and manipulation tasks, where prior goal-conditioned RL methods (including those based on graph search) fail to solve.

ICLR Conference 2022 Conference Paper

Conditional Contrastive Learning with Kernel

• Yao-Hung Hubert Tsai
• Tianqin Li
• Martin Q. Ma
• Han Zhao 0002
• Kun Zhang 0001
• Louis-Philippe Morency
• Ruslan Salakhutdinov

Conditional contrastive learning frameworks consider the conditional sampling procedure that constructs positive or negative data pairs conditioned on specific variables. Fair contrastive learning constructs negative pairs, for example, from the same gender (conditioning on sensitive information), which in turn reduces undesirable information from the learned representations; weakly supervised contrastive learning constructs positive pairs with similar annotative attributes (conditioning on auxiliary information), which in turn are incorporated into the representations. Although conditional contrastive learning enables many applications, the conditional sampling procedure can be challenging if we cannot obtain sufficient data pairs for some values of the conditioning variable. This paper presents Conditional Contrastive Learning with Kernel (CCL-K) that converts existing conditional contrastive objectives into alternative forms that mitigate the insufficient data problem. Instead of sampling data according to the value of the conditioning variable, CCL-K uses the Kernel Conditional Embedding Operator that samples data from all available data and assigns weights to each sampled data given the kernel similarity between the values of the conditioning variable. We conduct experiments using weakly supervised, fair, and hard negatives contrastive learning, showing CCL-K outperforms state-of-the-art baselines.

ICLR Conference 2022 Conference Paper

FILM: Following Instructions in Language with Modular Methods

• So Yeon Min
• Devendra Singh Chaplot
• Pradeep Ravikumar
• Yonatan Bisk
• Ruslan Salakhutdinov

Recent methods for embodied instruction following are typically trained end-to-end using imitation learning. This often requires the use of expert trajectories and low-level language instructions. Such approaches assume that neural states will integrate multimodal semantics to perform state tracking, building spatial memory, exploration, and long-term planning. In contrast, we propose a modular method with structured representations that (1) builds a semantic map of the scene and (2) performs exploration with a semantic search policy, to achieve the natural language goal. Our modular method achieves SOTA performance (24.46 %) with a substantial (8.17 % absolute) gap from previous work while using less data by eschewing both expert trajectories and low-level instructions. Leveraging low-level language, however, can further increase our performance (26.49 %). Our findings suggest that an explicit spatial memory and a semantic search policy can provide a stronger and more general representation for state-tracking and guidance, even in the absence of expert trajectories or low-level instructions.

ICLR Conference 2022 Conference Paper

Learning Weakly-supervised Contrastive Representations

• Yao-Hung Hubert Tsai
• Tianqin Li
• Weixin Liu
• Peiyuan Liao
• Ruslan Salakhutdinov
• Louis-Philippe Morency

We argue that a form of the valuable information provided by the auxiliary information is its implied data clustering information. For instance, considering hashtags as auxiliary information, we can hypothesize that an Instagram image will be semantically more similar with the same hashtags. With this intuition, we present a two-stage weakly-supervised contrastive learning approach. The first stage is to cluster data according to its auxiliary information. The second stage is to learn similar representations within the same cluster and dissimilar representations for data from different clusters. Our empirical experiments suggest the following three contributions. First, compared to conventional self-supervised representations, the auxiliary-information-infused representations bring the performance closer to the supervised representations, which use direct downstream labels as supervision signals. Second, our approach performs the best in most cases, when comparing our approach with other baseline representation learning methods that also leverage auxiliary data information. Third, we show that our approach also works well with unsupervised constructed clusters (e.g., no auxiliary information), resulting in a strong unsupervised representation learning approach.

ICML Conference 2022 Conference Paper

Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs

• Tianwei Ni
• Benjamin Eysenbach
• Ruslan Salakhutdinov

Many problems in RL, such as meta-RL, robust RL, generalization in RL, and temporal credit assignment, can be cast as POMDPs. In theory, simply augmenting model-free RL with memory-based architectures, such as recurrent neural networks, provides a general approach to solving all types of POMDPs. However, prior work has found that such recurrent model-free RL methods tend to perform worse than more specialized algorithms that are designed for specific types of POMDPs. This paper revisits this claim. We find that careful architecture and hyperparameter decisions can often yield a recurrent model-free implementation that performs on par with (and occasionally substantially better than) more sophisticated recent techniques. We compare to 21 environments from 6 prior specialized methods and find that our implementation achieves greater sample efficiency and asymptotic performance than these methods on 18/21 environments. We also release a simple and efficient implementation of recurrent model-free RL for future work to use as a baseline for POMDPs.

ICLR Conference 2022 Conference Paper

The Information Geometry of Unsupervised Reinforcement Learning

• Benjamin Eysenbach
• Ruslan Salakhutdinov
• Sergey Levine

How can a reinforcement learning (RL) agent prepare to solve downstream tasks if those tasks are not known a priori? One approach is unsupervised skill discovery, a class of algorithms that learn a set of policies without access to a reward function. Such algorithms bear a close resemblance to representation learning algorithms (e.g., contrastive learning) in supervised learning, in that both are pretraining algorithms that maximize some approximation to a mutual information objective. While prior work has shown that the set of skills learned by such methods can accelerate downstream RL tasks, prior work offers little analysis into whether these skill learning algorithms are optimal, or even what notion of optimality would be appropriate to apply to them. In this work, we show that unsupervised skill discovery algorithms based on mutual information maximization do not learn skills that are optimal for every possible reward function. However, we show that the distribution over skills provides an optimal initialization minimizing regret against adversarially-chosen reward functions, assuming a certain type of adaptation procedure. Our analysis also provides a geometric perspective on these skill learning methods.

NeurIPS Conference 2022 Conference Paper

Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks

• Minji Yoon
• John Palowitch
• Dustin Zelle
• Ziniu Hu
• Ruslan Salakhutdinov
• Bryan Perozzi

Data continuously emitted from industrial ecosystems such as social or e-commerce platforms are commonly represented as heterogeneous graphs (HG) composed of multiple node/edge types. State-of-the-art graph learning methods for HGs known as heterogeneous graph neural networks (HGNNs) are applied to learn deep context-informed node representations. However, many HG datasets from industrial applications suffer from label imbalance between node types. As there is no direct way to learn using labels rooted at different node types, HGNNs have been applied to only a few node types with abundant labels. We propose a zero-shot transfer learning module for HGNNs called a Knowledge Transfer Network (KTN) that transfers knowledge from label-abundant node types to zero-labeled node types through rich relational information given in the HG. KTN is derived from the theoretical relationship, which we introduce in this work, between distinct feature extractors for each node type given in an HGNN model. KTN improves the performance of 6 different types of HGNN models by up to 960% for inference on zero-labeled node types and outperforms state-of-the-art transfer learning baselines by up to 73% across 18 different transfer learning tasks on HGs.

ICLR Conference 2021 Conference Paper

C-Learning: Learning to Achieve Goals via Recursive Classification

• Benjamin Eysenbach
• Ruslan Salakhutdinov
• Sergey Levine

We study the problem of predicting and controlling the future state distribution of an autonomous agent. This problem, which can be viewed as a reframing of goal-conditioned reinforcement learning (RL), is centered around learning a conditional probability density function over future states. Instead of directly estimating this density function, we indirectly estimate this density function by training a classifier to predict whether an observation comes from the future. Via Bayes' rule, predictions from our classifier can be transformed into predictions over future states. Importantly, an off-policy variant of our algorithm allows us to predict the future state distribution of a new policy, without collecting new experience. This variant allows us to optimize functionals of a policy's future state distribution, such as the density of reaching a particular goal state. While conceptually similar to Q-learning, our work lays a principled foundation for goal-conditioned RL as density estimation, providing justification for goal-conditioned methods used in prior work. This foundation makes hypotheses about Q-learning, including the optimal goal-sampling ratio, which we confirm experimentally. Moreover, our proposed method is competitive with prior goal-conditioned RL methods.

ICLR Conference 2021 Conference Paper

Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation

• Emilio Parisotto
• Ruslan Salakhutdinov

Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on un-accelerated hardware such as CPUs, which likewise restricts model size to prevent intractable experiment run times. These "actor-latency" constrained settings present a major obstruction to the scaling up of model complexity that has recently been extremely successful in supervised learning. To be able to utilize large model capacity while still operating within the limits imposed by the system during acting, we develop an "Actor-Learner Distillation" (ALD) procedure that leverages a continual form of distillation that transfers learning progress from a large capacity learner model to a small capacity actor model. As a case study, we develop this procedure in the context of partially-observable environments, where transformer models have had large improvements over LSTMs recently, at the cost of significantly higher computational complexity. With transformer models as the learner and LSTMs as the actor, we demonstrate in several challenging memory environments that using Actor-Learner Distillation largely recovers the clear sample-efficiency gains of the transformer learner model while maintaining the fast inference and reduced total training time of the LSTM actor model.

ICML Conference 2021 Conference Paper

Information Obfuscation of Graph Neural Networks

• Peiyuan Liao
• Han Zhao 0002
• Keyulu Xu
• Tommi S. Jaakkola
• Geoffrey J. Gordon
• Stefanie Jegelka
• Ruslan Salakhutdinov

While the advent of Graph Neural Networks (GNNs) has greatly improved node and graph representation learning in many applications, the neighborhood aggregation scheme exposes additional vulnerabilities to adversaries seeking to extract node-level information about sensitive attributes. In this paper, we study the problem of protecting sensitive attributes by information obfuscation when learning with graph structured data. We propose a framework to locally filter out pre-determined sensitive attributes via adversarial training with the total variation and the Wasserstein distance. Our method creates a strong defense against inference attacks, while only suffering small loss in task performance. Theoretically, we analyze the effectiveness of our framework against a worst-case adversary, and characterize an inherent trade-off between maximizing predictive accuracy and minimizing information leakage. Experiments across multiple datasets from recommender systems, knowledge graphs and quantum chemistry demonstrate that the proposed approach provides a robust defense across various graph structures and tasks, while producing competitive GNN encoders for downstream tasks.

ICML Conference 2021 Conference Paper

Instabilities of Offline RL with Pre-Trained Neural Representation

• Ruosong Wang
• Yifan Wu
• Ruslan Salakhutdinov
• Sham M. Kakade

In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn) policies in scenarios where the data are collected from a distribution that substantially differs from that of the target policy to be evaluated. Recent theoretical advances have shown that such sample-efficient offline RL is indeed possible provided certain strong representational conditions hold, else there are lower bounds exhibiting exponential error amplification (in the problem horizon) unless the data collection distribution has only a mild distribution shift relative to the target policy. This work studies these issues from an empirical perspective to gauge how stable offline RL methods are. In particular, our methodology explores these ideas when using features from pre-trained neural networks, in the hope that these representations are powerful enough to permit sample efficient offline RL. Through extensive experiments on a range of tasks, we see that substantial error amplification does occur even when using such pre-trained representations (trained on the same task itself); we find offline RL is stable only under extremely mild distribution shift. The implications of these results, both from a theoretical and an empirical perspective, are that successful offline RL (where we seek to go beyond the low distribution shift regime) requires substantially stronger conditions beyond those which suffice for successful supervised learning.

NeurIPS Conference 2021 Conference Paper

MultiBench: Multiscale Benchmarks for Multimodal Representation Learning

• Paul Pu Liang
• Yiwei Lyu
• Xiang Fan
• Zetian Wu
• Yun Cheng
• Jason Wu
• Leslie (Yufan) Chen
• Peter Wu

Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. It is a challenging yet crucial area with numerous real-world applications in multimedia, affective computing, robotics, finance, human-computer interaction, and healthcare. Unfortunately, multimodal research has seen limited resources to study (1) generalization across domains and modalities, (2) complexity during training and inference, and (3) robustness to noisy and missing modalities. In order to accelerate progress towards understudied modalities and tasks while ensuring real-world robustness, we release MultiBench, a systematic and unified large-scale benchmark for multimodal learning spanning 15 datasets, 10 modalities, 20 prediction tasks, and 6 research areas. MultiBench provides an automated end-to-end machine learning pipeline that simplifies and standardizes data loading, experimental setup, and model evaluation. To enable holistic evaluation, MultiBench offers a comprehensive methodology to assess (1) generalization, (2) time and space complexity, and (3) modality robustness. MultiBench introduces impactful challenges for future research, including scalability to large-scale multimodal datasets and robustness to realistic imperfections. To accompany this benchmark, we also provide a standardized implementation of 20 core approaches in multimodal learning spanning innovations in fusion paradigms, optimization objectives, and training approaches. Simply applying methods proposed in different research areas can improve the state-of-the-art performance on 9/15 datasets. Therefore, MultiBench presents a milestone in unifying disjoint efforts in multimodal machine learning research and paves the way towards a better understanding of the capabilities and limitations of multimodal models, all the while ensuring ease of use, accessibility, and reproducibility. MultiBench, our standardized implementations, and leaderboards are publicly available, will be regularly updated, and welcomes inputs from the community.

ICLR Conference 2021 Conference Paper

Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers

• Benjamin Eysenbach
• Shreyas Chaudhari
• Swapnil Asawa
• Sergey Levine
• Ruslan Salakhutdinov

We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. Our approach stems from the idea that the agent's experience in the source domain should look similar to its experience in the target domain. Building off of a probabilistic view of RL, we achieve this goal by compensating for the difference in dynamics by modifying the reward function. This modified reward function is simple to estimate by learning auxiliary classifiers that distinguish source-domain transitions from target-domain transitions. Intuitively, the agent is penalized for transitions that would indicate that the agent is interacting with the source domain, rather than the target domain. Formally, we prove that applying our method in the source domain is guaranteed to obtain a near-optimal policy for the target domain, provided that the source and target domains satisfy a lightweight assumption. Our approach is applicable to domains with continuous states and actions and does not require learning an explicit model of the dynamics. On discrete and continuous control tasks, we illustrate the mechanics of our approach and demonstrate its scalability to high-dimensional~tasks.

ICML Conference 2021 Conference Paper

On Proximal Policy Optimization's Heavy-tailed Gradients

• Saurabh Garg
• Joshua Zhanson
• Emilio Parisotto
• Adarsh Prasad
• J. Zico Kolter
• Zachary C. Lipton
• Sivaraman Balakrishnan
• Ruslan Salakhutdinov

Modern policy gradient algorithms such as Proximal Policy Optimization (PPO) rely on an arsenal of heuristics, including loss clipping and gradient clipping, to ensure successful learning. These heuristics are reminiscent of techniques from robust statistics, commonly used for estimation in outlier-rich ("heavy-tailed") regimes. In this paper, we present a detailed empirical study to characterize the heavy-tailed nature of the gradients of the PPO surrogate reward function. We demonstrate that the gradients, especially for the actor network, exhibit pronounced heavy-tailedness and that it increases as the agent’s policy diverges from the behavioral policy (i. e. , as the agent goes further off policy). Further examination implicates the likelihood ratios and advantages in the surrogate reward as the main sources of the observed heavy-tailedness. We then highlight issues arising due to the heavy-tailed nature of the gradients. In this light, we study the effects of the standard PPO clipping heuristics, demonstrating that these tricks primarily serve to offset heavy-tailedness in gradients. Thus motivated, we propose incorporating GMOM, a high-dimensional robust estimator, into PPO as a substitute for three clipping tricks. Despite requiring less hyperparameter tuning, our method matches the performance of PPO (with all heuristics enabled) on a battery of MuJoCo continuous control tasks.

ICML Conference 2021 Conference Paper

Reasoning Over Virtual Knowledge Bases With Open Predicate Relations

• Haitian Sun
• Patrick Verga
• Bhuwan Dhingra
• Ruslan Salakhutdinov
• William W. Cohen

We present the Open Predicate Query Language (OPQL); a method for constructing a virtual KB (VKB) trained entirely from text. Large Knowledge Bases (KBs) are indispensable for a wide-range of industry applications such as question answering and recommendation. Typically, KBs encode world knowledge in a structured, readily accessible form derived from laborious human annotation efforts. Unfortunately, while they are extremely high precision, KBs are inevitably highly incomplete and automated methods for enriching them are far too inaccurate. Instead, OPQL constructs a VKB by encoding and indexing a set of relation mentions in a way that naturally enables reasoning and can be trained without any structured supervision. We demonstrate that OPQL outperforms prior VKB methods on two different KB reasoning tasks and, additionally, can be used as an external memory integrated into a language model (OPQL-LM) leading to improvements on two open-domain question answering tasks.

ICLR Conference 2021 Conference Paper

Self-supervised Learning from a Multi-view Perspective

• Yao-Hung Hubert Tsai
• Yue Wu 0001
• Ruslan Salakhutdinov
• Louis-Philippe Morency

As a subset of unsupervised representation learning, self-supervised representation learning adopts self-defined signals as supervision and uses the learned representation for downstream tasks, such as object detection and image captioning. Many proposed approaches for self-supervised learning follow naturally a multi-view perspective, where the input (e.g., original images) and the self-supervised signals (e.g., augmented images) can be seen as two redundant views of the data. Building from this multi-view perspective, this paper provides an information-theoretical framework to better understand the properties that encourage successful self-supervised learning. Specifically, we demonstrate that self-supervised learned representations can extract task-relevant information and discard task-irrelevant information. Our theoretical framework paves the way to a larger space of self-supervised learning objective design. In particular, we propose a composite objective that bridges the gap between prior contrastive and predictive learning objectives, and introduce an additional objective term to discard task-irrelevant information. To verify our analysis, we conduct controlled experiments to evaluate the impact of the composite objectives. We also explore our framework's empirical generalization beyond the multi-view perspective, where the cross-view redundancy may not be clearly observed.

ICLR Conference 2021 Conference Paper

Self-supervised Representation Learning with Relative Predictive Coding

• Yao-Hung Hubert Tsai
• Martin Q. Ma
• Muqiao Yang
• Han Zhao 0002
• Louis-Philippe Morency
• Ruslan Salakhutdinov

This paper introduces Relative Predictive Coding (RPC), a new contrastive representation learning objective that maintains a good balance among training stability, minibatch size sensitivity, and downstream task performance. The key to the success of RPC is two-fold. First, RPC introduces the relative parameters to regularize the objective for boundedness and low variance. Second, RPC contains no logarithm and exponential score functions, which are the main cause of training instability in prior contrastive objectives. We empirically verify the effectiveness of RPC on benchmark vision and speech self-supervised learning tasks. Lastly, we relate RPC with mutual information (MI) estimation, showing RPC can be used to estimate MI with low variance.

ICML Conference 2021 Conference Paper

Towards Understanding and Mitigating Social Biases in Language Models

• Paul Pu Liang
• Chiyu Wu
• Louis-Philippe Morency
• Ruslan Salakhutdinov

As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes. Among such real-world deployments are large-scale pretrained language models (LMs) that can be potentially dangerous in manifesting undesirable representational biases - harmful biases resulting from stereotyping that propagate negative generalizations involving gender, race, religion, and other social constructs. As a step towards improving the fairness of LMs, we carefully define several sources of representational biases before proposing new benchmarks and metrics to measure them. With these tools, we propose steps towards mitigating social biases during text generation. Our empirical results and human evaluation demonstrate effectiveness in mitigating bias while retaining crucial contextual information for high-fidelity text generation, thereby pushing forward the performance-fairness Pareto frontier.

ICML Conference 2021 Conference Paper

Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning

• Yue Wu 0001
• Shuangfei Zhai
• Nitish Srivastava
• Joshua M. Susskind
• Jian Zhang 0050
• Ruslan Salakhutdinov
• Hanlin Goh

Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration. However, existing Q-learning and actor-critic based off-policy RL algorithms fail when bootstrapping from out-of-distribution (OOD) actions or states. We hypothesize that a key missing ingredient from the existing methods is a proper treatment of uncertainty in the offline setting. We propose Uncertainty Weighted Actor-Critic (UWAC), an algorithm that detects OOD state-action pairs and down-weights their contribution in the training objectives accordingly. Implementation-wise, we adopt a practical and effective dropout-based uncertainty estimation method that introduces very little overhead over existing RL algorithms. Empirically, we observe that UWAC substantially improves model stability during training. In addition, UWAC out-performs existing offline RL methods on a variety of competitive tasks, and achieves significant performance gains over the state-of-the-art baseline on datasets with sparse demonstrations collected from human experts.

ICLR Conference 2020 Conference Paper

Capsules with Inverted Dot-Product Attention Routing

• Yao-Hung Hubert Tsai
• Nitish Srivastava
• Hanlin Goh
• Ruslan Salakhutdinov

We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote. The new mechanism 1) designs routing via inverted dot-product attention; 2) imposes Layer Normalization as normalization; and 3) replaces sequential iterative routing with concurrent iterative routing. When compared to previously proposed routing algorithms, our method improves performance on benchmark datasets such as CIFAR-10 and CIFAR-100, and it performs at-par with a powerful CNN (ResNet-18) with 4x fewer parameters. On a different task of recognizing digits from overlayed digit images, the proposed capsule model performs favorably against CNNs given the same number of layers and neurons per layer. We believe that our work raises the possibility of applying capsule networks to complex real-world tasks.

ICLR Conference 2020 Conference Paper

Differentiable Reasoning over a Virtual Knowledge Base

• Bhuwan Dhingra
• Manzil Zaheer
• Vidhisha Balachandran
• Graham Neubig
• Ruslan Salakhutdinov
• William W. Cohen

We consider the task of answering complex multi-hop questions using a corpus as a virtual knowledge base (KB). In particular, we describe a neural module, DrKIT, that traverses textual data like a KB, softly following paths of relations between mentions of entities in the corpus. At each step the module uses a combination of sparse-matrix TFIDF indices and a maximum inner product search (MIPS) on a special index of contextual representations of the mentions. This module is differentiable, so the full system can be trained end-to-end using gradient based methods, starting from natural language inputs. We also describe a pretraining scheme for the contextual representation encoder by generating hard negative examples using existing knowledge bases. We show that DrKIT improves accuracy by 9 points on 3-hop questions in the MetaQA dataset, cutting the gap between text-based and KB-based state-of-the-art by 70%. On HotpotQA, DrKIT leads to a 10% improvement over a BERT-based re-ranking approach to retrieving the relevant passages required to answer a question. DrKIT is also very efficient, processing up to 10-100x more queries per second than existing multi-hop systems.

IJCAI Conference 2020 Conference Paper

Embodied Multimodal Multitask Learning

• Devendra Singh Chaplot
• Lisa Lee
• Ruslan Salakhutdinov
• Devi Parikh
• Dhruv Batra

Visually-grounded embodied language learning models have recently shown to be effective at learning multiple multimodal tasks such as following navigational instructions and answering questions. In this paper, we address two key limitations of these models, (a) the inability to transfer the grounded knowledge across different tasks and (b) the inability to transfer to new words and concepts not seen during training using only a few examples. We propose a multitask model which facilitates knowledge transfer across tasks by disentangling the knowledge of words and visual attributes in the intermediate representations. We create scenarios and datasets to quantify cross-task knowledge transfer and show that the proposed model outperforms a range of baselines in simulated 3D environments. We also show that this disentanglement of representations makes our model modular and interpretable which allows for transfer to instructions containing new concepts.

ICLR Conference 2020 Conference Paper

Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks

• Sanjeev Arora
• Simon S. Du
• Zhiyuan Li 0005
• Ruslan Salakhutdinov
• Ruosong Wang
• Dingli Yu

Recent research shows that the following two models are equivalent: (a) infinitely wide neural networks (NNs) trained under l2 loss by gradient descent with infinitesimally small learning rate (b) kernel regression with respect to so-called Neural Tangent Kernels (NTKs) (Jacot et al., 2018). An efficient algorithm to compute the NTK, as well as its convolutional counterparts, appears in Arora et al. (2019a), which allowed studying performance of infinitely wide nets on datasets like CIFAR-10. However, super-quadratic running time of kernel methods makes them best suited for small-data tasks. We report results suggesting neural tangent kernels perform strongly on low-data tasks. 1. On a standard testbed of classification/regression tasks from the UCI database, NTK SVM beats the previous gold standard, Random Forests (RF), and also the corresponding finite nets. 2. On CIFAR-10 with 10 – 640 training samples, Convolutional NTK consistently beats ResNet-34 by 1% - 3%. 3. On VOC07 testbed for few-shot image classification tasks on ImageNet with transfer learning (Goyal et al., 2019), replacing the linear SVM currently used with a Convolutional NTK SVM consistently improves performance. 4. Comparing the performance of NTK with the finite-width net it was derived from, NTK behavior starts at lower net widths than suggested by theoretical analysis(Arora et al., 2019a). NTK’s efficacy may trace to lower variance of output.

ICLR Conference 2020 Conference Paper

Learning To Explore Using Active Neural SLAM

• Devendra Singh Chaplot
• Dhiraj Gandhi
• Saurabh Gupta 0001
• Abhinav Gupta 0001
• Ruslan Salakhutdinov

This work presents a modular and hierarchical approach to learn policies for exploring 3D environments, called `Active Neural SLAM'. Our approach leverages the strengths of both classical and learning-based methods, by using analytical path planners with learned SLAM module, and global and local policies. The use of learning provides flexibility with respect to input modalities (in the SLAM module), leverages structural regularities of the world (in global policies), and provides robustness to errors in state estimation (in local policies). Such use of learning within each module retains its benefits, while at the same time, hierarchical decomposition and modular training allow us to sidestep the high sample complexities associated with training end-to-end policies. Our experiments in visually and physically realistic simulated 3D environments demonstrate the effectiveness of our approach over past learning and geometry-based approaches. The proposed model can also be easily transferred to the PointGoal task and was the winning entry of the CVPR 2019 Habitat PointGoal Navigation Challenge.

IJCAI Conference 2019 Conference Paper

MineRL: A Large-Scale Dataset of Minecraft Demonstrations

• William H. Guss
• Brandon Houghton
• Nicholay Topin
• Phillip Wang
• Cayden Codel
• Manuela Veloso
• Ruslan Salakhutdinov

The sample inefficiency of standard deep reinforcement learning methods precludes their application to many real-world problems. Methods which leverage human demonstrations require fewer samples but have been researched less. As demonstrated in the computer vision and natural language processing communities, large-scale datasets have the capacity to facilitate research by serving as an experimental and benchmarking platform for new methods. However, existing datasets compatible with reinforcement learning simulators do not have sufficient scale, structure, and quality to enable the further development and evaluation of methods focused on using human examples. Therefore, we introduce a comprehensive, large-scale, simulator-paired dataset of human demonstrations: MineRL. The dataset consists of over 60 million automatically annotated state-action pairs across a variety of related tasks in Minecraft, a dynamic, 3D, open-world environment. We present a novel data collection scheme which allows for the ongoing introduction of new tasks and the gathering of complete state information suitable for a variety of methods. We demonstrate the hierarchality, diversity, and scale of the MineRL dataset. Further, we show the difficulty of the Minecraft domain along with the potential of MineRL in developing techniques to solve key research challenges within it.

AAAI Conference 2019 Conference Paper

Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function

• Devendra Singh Sachan
• Manzil Zaheer
• Ruslan Salakhutdinov

In this paper, we study bidirectional LSTM network for the task of text classification using both supervised and semisupervised approaches. Several prior works have suggested that either complex pretraining schemes using unsupervised methods such as language modeling (Dai and Le 2015; Miyato, Dai, and Goodfellow 2016) or complicated models (Johnson and Zhang 2017) are necessary to achieve a high classification accuracy. However, we develop a training strategy that allows even a simple BiLSTM model, when trained with cross-entropy loss, to achieve competitive results compared with more complex approaches. Furthermore, in addition to cross-entropy loss, by using a combination of entropy minimization, adversarial, and virtual adversarial losses for both labeled and unlabeled data, we report state-of-theart results for text classification task on several benchmark datasets. In particular, on the ACL-IMDB sentiment analysis and AG-News topic classification datasets, our method outperforms current approaches by a substantial margin. We also show the generality of the mixed objective function by improving the performance on relation extraction task. 1

ICLR Conference 2018 Conference Paper

Breaking the Softmax Bottleneck: A High-Rank RNN Language Model

• Zhilin Yang 0001
• Zihang Dai
• Ruslan Salakhutdinov
• William W. Cohen

We formulate language modeling as a matrix factorization problem, and show that the expressiveness of Softmax-based models (including the majority of neural language models) is limited by a Softmax bottleneck. Given that natural language is highly context-dependent, this further implies that in practice Softmax with distributed word embeddings does not have enough capacity to model natural language. We propose a simple and effective method to address this issue, and improve the state-of-the-art perplexities on Penn Treebank and WikiText-2 to 47.69 and 40.68 respectively. The proposed method also excels on the large-scale 1B Word dataset, outperforming the baseline by over 5.6 points in perplexity.

ICML Conference 2018 Conference Paper

Gated Path Planning Networks

• Lisa Lee
• Emilio Parisotto
• Devendra Singh Chaplot
• Eric P. Xing
• Ruslan Salakhutdinov

Value Iteration Networks (VINs) are effective differentiable path planning modules that can be used by agents to perform navigation while still maintaining end-to-end differentiability of the entire architecture. Despite their effectiveness, they suffer from several disadvantages including training instability, random seed sensitivity, and other optimization problems. In this work, we reframe VINs as recurrent-convolutional networks which demonstrates that VINs couple recurrent convolutions with an unconventional max-pooling activation. From this perspective, we argue that standard gated recurrent update equations could potentially alleviate the optimization issues plaguing VIN. The resulting architecture, which we call the Gated Path Planning Network, is shown to empirically outperform VIN on a variety of metrics such as learning speed, hyperparameter sensitivity, iteration count, and even generalization. Furthermore, we show that this performance gap is consistent across different maze transition types, maze sizes and even show success on a challenging 3D environment, where the planner is only provided with first-person RGB images.

AAAI Conference 2018 Conference Paper

Gated-Attention Architectures for Task-Oriented Language Grounding

• Devendra Singh Chaplot
• Kanthashree Mysore Sathyendra
• Rama Kumar Pasumarthi
• Dheeraj Rajagopal
• Ruslan Salakhutdinov

To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it to visual elements and actions in the environment. This problem is called task-oriented language grounding. We propose an end-to-end trainable neural architecture for task-oriented language grounding in 3D environments which assumes no prior linguistic or perceptual knowledge and requires only raw pixels from the environment and the natural language instruction as input. The proposed model combines the image and text representations using a Gated-Attention mechanism and learns a policy to execute the natural language instruction using standard reinforcement and imitation learning methods. We show the effectiveness of the proposed model on unseen instructions as well as unseen maps, both quantitatively and qualitatively. We also introduce a novel environment based on a 3D game engine to simulate the challenges of task-oriented language grounding over a rich set of instructions and environment states.

AAAI Conference 2018 Conference Paper

Knowledge-based Word Sense Disambiguation using Topic Models

• Devendra Singh Chaplot
• Ruslan Salakhutdinov

Word Sense Disambiguation is an open problem in Natural Language Processing which is particularly challenging and useful in the unsupervised setting where all the words in any given text need to be disambiguated without using any labeled data. Typically WSD systems use the sentence or a small window of words around the target word as the context for disambiguation because their computational complexity scales exponentially with the size of the context. In this paper, we leverage the formalism of topic model to design a WSD system that scales linearly with the number of words in the context. As a result, our system is able to utilize the whole document as the context for a word to be disambiguated. The proposed method is a variant of Latent Dirichlet Allocation in which the topic proportions for a document are replaced by synset proportions. We further utilize the information in the WordNet by assigning a non-uniform prior to synset distribution over words and a logistic-normal prior for document distribution over synsets. We evaluate the proposed method on Senseval-2, Senseval-3, SemEval-2007, SemEval- 2013 and SemEval-2015 English All-Word WSD datasets and show that it outperforms the state-of-the-art unsupervised knowledge-based WSD system by a significant margin.

ICML Conference 2018 Conference Paper

Structured Control Nets for Deep Reinforcement Learning

• Mario Srouji
• Jian Zhang 0050
• Ruslan Salakhutdinov

In recent years, Deep Reinforcement Learning has made impressive advances in solving several important benchmark problems for sequential decision making. Many control applications use a generic multilayer perceptron (MLP) for non-vision parts of the policy network. In this work, we propose a new neural network architecture for the policy network representation that is simple yet effective. The proposed Structured Control Net (SCN) splits the generic MLP into two separate sub-modules: a nonlinear control module and a linear control module. Intuitively, the nonlinear control is for forward-looking and global control, while the linear control stabilizes the local dynamics around the residual of global control. We hypothesize that this will bring together the benefits of both linear and nonlinear policies: improve training sample efficiency, final episodic reward, and generalization of learned policy, while requiring a smaller network and being generally applicable to different training methods. We validated our hypothesis with competitive results on simulations from OpenAI MuJoCo, Roboschool, Atari, and a custom urban driving environment, with various ablation and generalization tests, trained with multiple black-box and policy gradient training methods. The proposed architecture has the potential to improve upon broader control tasks by incorporating problem specific priors into the architecture. As a case study, we demonstrate much improved performance for locomotion tasks by emulating the biological central pattern generators (CPGs) as the nonlinear part of the architecture.

ICML Conference 2018 Conference Paper

Transformation Autoregressive Networks

• Junier B. Oliva
• Avinava Dubey
• Manzil Zaheer
• Barnabás Póczos
• Ruslan Salakhutdinov
• Eric P. Xing
• Jeff G. Schneider

The fundamental task of general density estimation $p(x)$ has been of keen interest to machine learning. In this work, we attempt to systematically characterize methods for density estimation. Broadly speaking, most of the existing methods can be categorized into either using: a ) autoregressive models to estimate the conditional factors of the chain rule, $p(x_{i}\, |\, x_{i-1}, \ldots)$; or b ) non-linear transformations of variables of a simple base distribution. Based on the study of the characteristics of these categories, we propose multiple novel methods for each category. For example we propose RNN based transformations to model non-Markovian dependencies. Further, through a comprehensive study over both real world and synthetic data, we show that jointly leveraging transformations of variables and autoregressive conditional models, results in a considerable improvement in performance. We illustrate the use of our models in outlier detection and image modeling. Finally we introduce a novel data driven framework for learning a family of distributions.

ICML Conference 2017 Conference Paper

Improved Variational Autoencoders for Text Modeling using Dilated Convolutions

• Zichao Yang
• Zhiting Hu
• Ruslan Salakhutdinov
• Taylor Berg-Kirkpatrick

Recent work on generative text modeling has found that variational autoencoders (VAE) with LSTM decoders perform worse than simpler LSTM language models (Bowman et al. , 2015). This negative result is so far poorly understood, but has been attributed to the propensity of LSTM decoders to ignore conditioning information from the encoder. In this paper, we experiment with a new type of decoder for VAE: a dilated CNN. By changing the decoder’s dilation architecture, we control the size of context from previously generated words. In experiments, we find that there is a trade-off between contextual capacity of the decoder and effective use of encoding information. We show that when carefully managed, VAEs can outperform LSTM language models. We demonstrate perplexity gains on two datasets, representing the first positive language modeling result with VAE. Further, we conduct an in-depth investigation of the use of VAE (with our new decoding architecture) for semi-supervised and unsupervised labeling tasks, demonstrating gains over several strong baselines.

ICML Conference 2017 Conference Paper

Toward Controlled Generation of Text

• Zhiting Hu
• Zichao Yang
• Xiaodan Liang
• Ruslan Salakhutdinov
• Eric P. Xing

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible text sentences, whose attributes are controlled by learning disentangled latent representations with designated semantics. We propose a new neural generative model which combines variational auto-encoders (VAEs) and holistic attribute discriminators for effective imposition of semantic structures. The model can alternatively be seen as enhancing VAEs with the wake-sleep algorithm for leveraging fake samples as extra training data. With differentiable approximation to discrete text samples, explicit constraints on independent attribute controls, and efficient collaborative learning of generator and discriminators, our model learns interpretable representations from even only word annotations, and produces short sentences with desired attributes of sentiment and tenses. Quantitative experiments using trained classifiers as evaluators validate the accuracy of sentence and attribute generation.

ICLR Conference 2016 Conference Paper

Generating Images from Captions with Attention

• Elman Mansimov
• Emilio Parisotto
• Jimmy Ba
• Ruslan Salakhutdinov

Motivated by the recent progress in generative models, we introduce a model that generates images from natural language descriptions. The proposed model iteratively draws patches on a canvas, while attending to the relevant words in the description. After training on Microsoft COCO, we compare our model with several baseline generative models on image generation and retrieval tasks. We demonstrate that our model produces higher quality samples than other approaches and generates images with novel scene compositions corresponding to previously unseen captions in the dataset.

ICML Conference 2016 Conference Paper

Revisiting Semi-Supervised Learning with Graph Embeddings

• Zhilin Yang 0001
• William W. Cohen
• Ruslan Salakhutdinov

We present a semi-supervised learning framework based on graph embeddings. Given a graph between instances, we train an embedding for each instance to jointly predict the class label and the neighborhood context in the graph. We develop both transductive and inductive variants of our method. In the transductive variant of our method, the class labels are determined by both the learned embeddings and input feature vectors, while in the inductive variant, the embeddings are defined as a parametric function of the feature vectors, so predictions can be made on instances not seen during training. On a large and diverse set of benchmark tasks, including text classification, distantly supervised entity extraction, and entity classification, we show improved performance over many of the existing models.

ICML Conference 2015 Conference Paper

Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix

• Roger B. Grosse
• Ruslan Salakhutdinov

Second-order optimization methods, such as natural gradient, are difficult to apply to high-dimensional problems, because they require approximately solving large linear systems. We present FActorized Natural Gradient (FANG), an approximation to natural gradient descent where the Fisher matrix is approximated with a Gaussian graphical model whose precision matrix can be computed efficiently. We analyze the Fisher matrix for a small RBM and derive an extremely sparse graphical model which is a good match to the covariance of the sufficient statistics. Our experiments indicate that FANG allows RBMs to be trained more efficiently compared with stochastic gradient descent. Additionally, our analysis yields insight into the surprisingly good performance of the “centering trick” for training RBMs.

ICML Conference 2015 Conference Paper

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

• Kelvin Xu
• Jimmy Ba
• Jamie Kiros
• Kyunghyun Cho
• Aaron C. Courville
• Ruslan Salakhutdinov
• Richard S. Zemel
• Yoshua Bengio

Inspired by recent work in machine translation and object detection, we introduce an attention based model that automatically learns to describe the content of images. We describe how we can train this model in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound. We also show through visualization how the model is able to automatically learn to fix its gaze on salient objects while generating the corresponding words in the output sequence. We validate the use of attention with state-of-the-art performance on three benchmark datasets: Flickr8k, Flickr30k and MS COCO.

ICML Conference 2015 Conference Paper

Unsupervised Learning of Video Representations using LSTMs

• Nitish Srivastava
• Elman Mansimov
• Ruslan Salakhutdinov

We use Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length representation. This representation is decoded using single or multiple decoder LSTMs to perform different tasks, such as reconstructing the input sequence, or predicting the future sequence. We experiment with two kinds of input sequences – patches of image pixels and high-level representations (“percepts") of video frames extracted using a pretrained convolutional net. We explore different design choices such as whether the decoder LSTMs should condition on the generated output. We analyze the outputs of the model qualitatively to see how well the model can extrapolate the learned video representation into the future and into the past. We further evaluate the representations by finetuning them for a supervised learning problem – human action recognition on the UCF-101 and HMDB-51 datasets. We show that the representations help improve classification accuracy, especially when there are only few training examples. Even models pretrained on unrelated datasets (300 hours of YouTube videos) can help action recognition performance.

JMLR Journal 2014 Journal Article

Dropout: A Simple Way to Prevent Neural Networks from Overfitting

• Nitish Srivastava
• Geoffrey Hinton
• Alex Krizhevsky
• Ilya Sutskever
• Ruslan Salakhutdinov

Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different thinned networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets. [abs] [ pdf ][ bib ] &copy JMLR 2014. ( edit, beta )

JMLR Journal 2014 Journal Article

Multimodal Learning with Deep Boltzmann Machines

• Nitish Srivastava
• Ruslan Salakhutdinov

Data often consists of multiple diverse modalities. For example, images are tagged with textual information and videos are accompanied by audio. Each modality is characterized by having distinct statistical properties. We propose a Deep Boltzmann Machine for learning a generative model of such multimodal data. We show that the model can be used to create fused representations by combining features across modalities. These learned representations are useful for classification and information retrieval. By sampling from the conditional distributions over each data modality, it is possible to create these representations even when some data modalities are missing. We conduct experiments on bi-modal image-text and audio-video data. The fused representation achieves good classification results on the MIR-Flickr data set matching or outperforming other deep models as well as SVM based models that use Multiple Kernel Learning. We further demonstrate that this multimodal model helps classification and retrieval even when only unimodal data is available at test time. [abs] [ pdf ][ bib ] &copy JMLR 2014. ( edit, beta )

ICML Conference 2014 Conference Paper

Multimodal Neural Language Models

• Jamie Kiros
• Ruslan Salakhutdinov
• Richard S. Zemel

We introduce two multimodal neural language models: models of natural language that can be conditioned on other modalities. An image-text multimodal neural language model can be used to retrieve images given complex sentence queries, retrieve phrase descriptions given image queries, as well as generate text conditioned on images. We show that in the case of image-text modelling we can jointly learn word representations and image features by training our models together with a convolutional network. Unlike many of the existing methods, our approach can generate sentence descriptions for images without the use of templates, structured prediction, and/or syntactic trees. While we focus on image-text modelling, our algorithms can be easily applied to other modalities such as audio.

YNIMG Journal 2014 Journal Article

Restricted Boltzmann machines for neuroimaging: An application in identifying intrinsic networks

• R. Devon Hjelm
• Vince D. Calhoun
• Ruslan Salakhutdinov
• Elena A. Allen
• Tulay Adali
• Sergey M. Plis

Matrix factorization models are the current dominant approach for resolving meaningful data-driven features in neuroimaging data. Among them, independent component analysis (ICA) is arguably the most widely used for identifying functional networks, and its success has led to a number of versatile extensions to group and multimodal data. However there are indications that ICA may have reached a limit in flexibility and representational capacity, as the majority of such extensions are case-driven, custom-made solutions that are still contained within the class of mixture models. In this work, we seek out a principled and naturally extensible approach and consider a probabilistic model known as a restricted Boltzmann machine (RBM). An RBM separates linear factors from functional brain imaging data by fitting a probability distribution model to the data. Importantly, the solution can be used as a building block for more complex (deep) models, making it naturally suitable for hierarchical and multimodal extensions that are not easily captured when using linear factorizations alone. We investigate the capability of RBMs to identify intrinsic networks and compare its performance to that of well-known linear mixture models, in particular ICA. Using synthetic and real task fMRI data, we show that RBMs can be used to identify networks and their temporal activations with accuracy that is equal or greater than that of factorization models. The demonstrated effectiveness of RBMs supports its use as a building block for deeper models, a significant prospect for future neuroimaging research.

UAI Conference 2013 Conference Paper

Modeling Documents with Deep Boltzmann Machines

• Nitish Srivastava
• Ruslan Salakhutdinov
• Geoffrey E. Hinton

We introduce a type of Deep Boltzmann Machine (DBM) that is suitable for extracting distributed semantic representations from a large unstructured collection of documents. We overcome the apparent difficulty of training a DBM with judicious parameter tying. This enables an efficient pretraining algorithm and a state initialization scheme for fast inference. The model can be trained just as efficiently as a standard Restricted Boltzmann Machine. Our experiments show that the model assigns better log probability to unseen data than the Replicated Softmax model. Features extracted from our model outperform LDA, Replicated Softmax, and DocNADE models on document retrieval and document classification tasks.

ICML Conference 2013 Conference Paper

Tensor Analyzers

• Yichuan Tang
• Ruslan Salakhutdinov
• Geoffrey E. Hinton

Factor Analysis is a statistical method that seeks to explain linear variations in data by using unobserved latent variables. Due to its additive nature, it is not suitable for modeling data that is generated by multiple groups of latent factors which interact multiplicatively. In this paper, we introduce Tensor Analyzers which are a multilinear generalization of Factor Analyzers. We describe an efficient way of sampling from the posterior distribution over factor values and we demonstrate that these samples can be used in the EM algorithm for learning interesting mixture models of natural image patches. Tensor Analyzers can also accurately recognize a face under significant pose and illumination variations when given only one previous image of that face. We also show that Tensor Analyzers can be trained in an unsupervised, semi-supervised, or fully supervised settings.

ICML Conference 2012 Conference Paper

Deep Lambertian Networks

• Yichuan Tang
• Ruslan Salakhutdinov
• Geoffrey E. Hinton

ICML Conference 2012 Conference Paper

Deep Mixtures of Factor Analysers

• Yichuan Tang
• Ruslan Salakhutdinov
• Geoffrey E. Hinton

UAI Conference 2012 Conference Paper

Exploiting compositionality to explore a large space of model structures

• Roger B. Grosse
• Ruslan Salakhutdinov
• William T. Freeman
• Joshua B. Tenenbaum

The recent proliferation of richly structured probabilistic models raises the question of how to automatically determine an appropriate model for a dataset. We investigate this question for a space of matrix decomposition models which can express a variety of widely used models from unsupervised learning. To enable model selection, we organize these models into a context-free grammar which generates a wide variety of structures through the compositional application of a few simple rules. We use our grammar to generically and efficiently infer latent components and estimate predictive likelihood for nearly 2500 structures using a small toolbox of reusable algorithms. Using a greedy search over our grammar, we automatically choose the decomposition structure from raw data by evaluating only a small fraction of all models. The proposed method typically finds the correct structure for synthetic data and backs off gracefully to simpler models under heavy noise. It learns sensible structures for datasets as diverse as image patches, motion capture, 20 Questions, and U.S. Senate votes, all using exactly the same code.

ICML Conference 2010 Conference Paper

Learning Deep Boltzmann Machines using Adaptive MCMC

• Ruslan Salakhutdinov

ICML Conference 2009 Conference Paper

Evaluation methods for topic models

• Hanna M. Wallach
• Iain Murray 0001
• Ruslan Salakhutdinov
• David M. Mimno

ICML Conference 2009 Conference Paper

Learning nonlinear dynamic models

• John Langford 0001
• Ruslan Salakhutdinov
• Tong Zhang 0001

We present a novel approach for learning nonlinear dynamic models, which leads to a new set of tools capable of solving problems that are otherwise difficult. We provide theory showing this new approach is consistent for models with long range structure, and apply the approach to motion capture and high-dimensional video data, yielding results superior to standard alternatives.

ICML Conference 2009 Conference Paper

Workshop summary: Workshop on learning feature hierarchies

• Kai Yu
• Ruslan Salakhutdinov
• Yann LeCun
• Geoffrey E. Hinton
• Yoshua Bengio

ICML Conference 2008 Conference Paper

Bayesian probabilistic matrix factorization using Markov chain Monte Carlo

• Ruslan Salakhutdinov
• Andriy Mnih

Low-rank matrix approximation methods provide one of the simplest and most effective approaches to collaborative filtering. Such models are usually fitted to data by finding a MAP estimate of the model parameters, a procedure that can be performed efficiently even on very large datasets. However, unless the regularization parameters are tuned carefully, this approach is prone to overfitting because it finds a single point estimate of the parameters. In this paper we present a fully Bayesian treatment of the Probabilistic Matrix Factorization (PMF) model in which model capacity is controlled automatically by integrating over all model parameters and hyperparameters. We show that Bayesian PMF models can be efficiently trained using Markov chain Monte Carlo methods by applying them to the Netflix dataset, which consists of over 100 million movie ratings. The resulting models achieve significantly higher prediction accuracy than PMF models trained using MAP estimation.

ICML Conference 2008 Conference Paper

On the quantitative analysis of deep belief networks

• Ruslan Salakhutdinov
• Iain Murray 0001

Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allowed these models to be applied successfully in many application domains. The main building block of a DBN is a bipartite undirected graphical model called a restricted Boltzmann machine (RBM). Due to the presence of the partition function, model selection, complexity control, and exact maximum likelihood learning in RBM's are intractable. We show that Annealed Importance Sampling (AIS) can be used to efficiently estimate the partition function of an RBM, and we present a novel AIS scheme for comparing RBM's with different architectures. We further show how an AIS estimator, along with approximate inference, can be used to estimate a lower bound on the log-probability that a DBN model with multiple hidden layers assigns to the test data . This is, to our knowledge, the first step towards obtaining quantitative results that would allow us to directly assess the performance of Deep Belief Networks as generative models of data.

ICML Conference 2007 Conference Paper

Restricted Boltzmann machines for collaborative filtering

• Ruslan Salakhutdinov
• Andriy Mnih
• Geoffrey E. Hinton

Most of the existing approaches to collaborative filtering cannot handle very large data sets. In this paper we show how a class of two-layer undirected graphical models, called Restricted Boltzmann Machines (RBM's), can be used to model tabular data, such as user's ratings of movies. We present efficient learning and inference procedures for this class of models and demonstrate that RBM's can be successfully applied to the Netflix data set, containing over 100 million user/movie ratings. We also show that RBM's slightly outperform carefully-tuned SVD models. When the predictions of multiple RBM models and multiple SVD models are linearly combined, we achieve an error rate that is well over 6% better than the score of Netflix's own system.

ICML Conference 2003 Conference Paper

Adaptive Overrelaxed Bound Optimization Methods

• Ruslan Salakhutdinov
• Sam T. Roweis

UAI Conference 2003 Conference Paper

On the Convergence of Bound Optimization Algorithms

• Ruslan Salakhutdinov
• Sam T. Roweis
• Zoubin Ghahramani

Many practitioners who use the EM algorithm complain that it is sometimes slow. When does this happen, and what can be done about it? In this paper, we study the general class of bound optimization algorithms --- including Expectation-Maximization, Iterative Scaling and CCCP --- and their relationship to direct optimization algorithms such as gradient-based methods for parameter learning. We derive a general relationship between the updates performed by bound optimization methods and those of gradient and second-order methods and identify analytic conditions under which bound optimization algorithms exhibit quasi-Newton behavior, and conditions under which they possess poor, first-order convergence. Based on this analysis, we consider several specific algorithms, interpret and analyze their convergence properties and provide some recipes for preprocessing input to these algorithms to yield faster convergence behavior. We report empirical results supporting our analysis and showing that simple data preprocessing can result in dramatically improved performance of bound optimizers in practice

ICML Conference 2003 Conference Paper

Optimization with EM and Expectation-Conjugate-Gradient

• Ruslan Salakhutdinov
• Sam T. Roweis
• Zoubin Ghahramani