Jiayu Zhou

AAAI Conference 2026 Conference Paper

Gentle Manipulation Policy Learning via Demonstrations from VLM Planned Atomic Skills

• Jiayu Zhou
• Qiwei Wu
• Jian Li
• Zhe Chen
• Xiaogang Xiong
• Renjing Xu

Autonomous execution of long-horizon, contact-rich manipulation tasks traditionally requires extensive real-world data and expert engineering, posing significant cost and scalability challenges. This paper proposes a novel framework integrating hierarchical semantic decomposition, reinforcement learning (RL), visual language models (VLMs), and knowledge distillation to overcome these limitations. Complex tasks are decomposed into atomic skills, with RL-trained policies for each primitive exclusively in simulation. Crucially, our RL formulation incorporates explicit force constraints to prevent object damage during delicate interactions. VLMs perform high-level task decomposition and skill planning, generating diverse expert demonstrations. These are distilled into a unified policy via Visual-Tactile Diffusion Policy for end-to-end execution. We conduct comprehensive ablation studies exploring different VLM-based task planners to identify optimal demonstration generation pipelines, and systematically compare imitation learning algorithms for skill distillation. Extensive simulation experiments and physical deployment validate that our approach achieves policy learning for long-horizon manipulation without costly human demonstrations, while the VLM-guided atomic skill framework enables scalable generalization to diverse tasks.

IJCAI Conference 2025 Conference Paper

Enhancing Automated Grading in Science Education through LLM-Driven Causal Reasoning and Multimodal Analysis

• Haohao Zhu
• Tingting Li
• Peng He
• Jiayu Zhou

Automated assessment of open responses in K–12 science education poses significant challenges due to the multimodal nature of student work, which often integrates textual explanations, drawings, and handwritten elements. Traditional evaluation methods that focus solely on textual analysis fail to capture the full breadth of student reasoning and are susceptible to biases such as handwriting neatness or answer length. In this paper, we propose a novel LLM-augmented multimodal evaluation framework that addresses these limitations through a comprehensive, bias-corrected grading system. Our approach leverages LLMs to generate causal knowledge graphs that encapsulate the essential conceptual relationships in student responses, comparing these graphs with those derived automatically from the rubrics and submissions. Experimental results demonstrate that our framework improves grading accuracy and consistency over deep supervised learning and few-shot LLM baselines.

ECAI Conference 2025 Conference Paper

Owen Sampling Accelerates Contribution Estimation in Federated Learning

• Hossein KhademSohi
• Hadi Hemmati
• Jiayu Zhou
• Steve Drew

Federated Learning (FL) aggregates information from multiple clients to train a shared global model without exposing raw data. Accurately estimating each client’s contribution is essential not just for fair rewards, but for selecting the most useful clients so the global model converges faster. The Shapley value is the principled choice for this, yet exact computation scales exponentially with the number of clients, making it infeasible for real-world FL deployments with many participants. In this paper, we propose FedOwen, an efficient federated contribution evaluation framework adopting Owen sampling to approximate Shapley values under the same total evaluation budget as the existing methods, while keeping the approximation error below a small threshold. In addition, FedOwen applies an adaptive client selection strategy that balances exploiting high-value clients with exploring under-sampled ones, avoiding bias toward a narrow subset, and uncovering rare but informative data. Under a fixed valuation cost, FedOwen achieves up to 23% improvement in final model accuracy within the same number of communication rounds, compared to state-of-the-art baselines on non-IID benchmarks. Code: https: //github. com/hoseinkhs/AdaptiveSelectionFL [17]

IROS Conference 2024 Conference Paper

RTTF: Rapid Tactile Transfer Framework for Contact-Rich Manipulation Tasks

• Qiwei Wu 0001
• Xuanbin Peng
• Jiayu Zhou
• Zhuoran Sun
• Xiaogang Xiong
• Yunjiang Lou

An increasing number of robotic manipulation tasks now use optical tactile sensors to provide tactile feedback, making tactile servo control a crucial aspect of robotic operations. This paper presents a rapid tactile transfer framework (RTTF) that achieves optical-tactile image sim2real transfer and robust tactile servo control using limited paired data. The sim2real aspect of RTTF employs a semi-supervised approach, beginning with pretraining the latent space representations of tactile images and subsequently mapping different tactile image domains to a shared latent space within a simulated tactile image domain. This latent space, combined with the proprioceptive information of the robotic arm, is then integrated into a privileged learning framework for policy training, which results in a deployable tactile control policy. Our results demonstrate the robustness of the proposed framework in achieving task objectives across different tactile sensors with varying physical parameters. Furthermore, manipulators equipped with tactile sensors, allow for rapid training and deployment for diverse contact-rich tasks, including object pushing and surface following.

ICLR Conference 2024 Conference Paper

Safe and Robust Watermark Injection with a Single OoD Image

• Shuyang Yu
• Junyuan Hong
• Haobo Zhang 0002
• Haotao Wang
• Zhangyang Wang
• Jiayu Zhou

Training a high-performance deep neural network requires large amounts of data and computational resources. Protecting the intellectual property (IP) and commercial ownership of a deep model is challenging yet increasingly crucial. A major stream of watermarking strategies implants verifiable backdoor triggers by poisoning training samples, but these are often unrealistic due to data privacy and safety concerns and are vulnerable to minor model changes such as fine-tuning. To overcome these challenges, we propose a safe and robust backdoor-based watermark injection technique that leverages the diverse knowledge from a single out-of-distribution (OoD) image, which serves as a secret key for IP verification. The independence of training data makes it agnostic to third-party promises of IP security. We induce robustness via random perturbation of model parameters during watermark injection to defend against common watermark removal attacks, including fine-tuning, pruning, and model extraction. Our experimental results demonstrate that the proposed watermarking approach is not only time- and sample-efficient without training data, but also robust against the watermark removal attacks above.

JAIR Journal 2023 Journal Article

A Unified Linear Speedup Analysis of Federated Averaging and Nesterov FedAvg

• Zhaonan Qu
• Kaixiang Lin
• Zhaojian Li
• Jiayu Zhou
• Zhengyuan Zhou

Federated learning (FL) learns a model jointly from a set of participating devices without sharing each other’s privately held data. The characteristics of non-i.i.d. data across the network, low device participation, high communication costs, and the mandate that data remain private bring challenges in understanding the convergence of FL algorithms, particularly regarding how convergence scales with the number of participating devices. In this paper, we focus on Federated Averaging (FedAvg), one of the most popular and effective FL algorithms in use today, as well as its Nesterov accelerated variant, and conduct a systematic study of how their convergence scale with the number of participating devices under non-i.i.d. data and partial participation in convex settings. We provide a unified analysis that establishes convergence guarantees for FedAvg under strongly convex, convex, and overparameterized strongly convex problems. We show that FedAvg enjoys linear speedup in each case, although with different convergence rates and communication efficiencies. For strongly convex and convex problems, we also characterize the corresponding convergence rates for the Nesterov accelerated FedAvg algorithm, which are the first linear speedup guarantees for momentum variants of FedAvg in convex settings. Empirical studies of the algorithms in various settings have supported our theoretical results.

AAAI Conference 2023 Conference Paper

Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning

• Junyuan Hong
• Haotao Wang
• Zhangyang Wang
• Jiayu Zhou

Federated learning (FL) emerges as a popular distributed learning schema that learns a model from a set of participating users without sharing raw data. One major challenge of FL comes with heterogeneous users, who may have distributionally different (or non-iid) data and varying computation resources. As federated users would use the model for prediction, they often demand the trained model to be robust against malicious attackers at test time. Whereas adversarial training (AT) provides a sound solution for centralized learning, extending its usage for federated users has imposed significant challenges, as many users may have very limited training data and tight computational budgets, to afford the data-hungry and costly AT. In this paper, we study a novel FL strategy: propagating adversarial robustness from rich-resource users that can afford AT, to those with poor resources that cannot afford it, during federated learning. We show that existing FL techniques cannot be effectively integrated with the strategy to propagate robustness among non-iid users and propose an efficient propagation approach by the proper use of batch-normalization. We demonstrate the rationality and effectiveness of our method through extensive experiments. Especially, the proposed method is shown to grant federated models remarkable robustness even when only a small portion of users afford AT during learning. Source code can be accessed at https://github.com/illidanlab/FedRBN.

TMLR Journal 2023 Journal Article

How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts

• Haotao Wang
• Junyuan Hong
• Jiayu Zhou
• Zhangyang Wang

Increasing concerns have been raised on deep learning fairness in recent years. Existing fairness-aware machine learning methods mainly focus on the fairness of in-distribution data. However, in real-world applications, it is common to have distribution shift between the training and test data. In this paper, we first show that the fairness achieved by existing methods can be easily broken by slight distribution shifts. To solve this problem, we propose a novel fairness learning method termed CUrvature MAtching (CUMA), which can achieve robust fairness generalizable to unseen domains with unknown distributional shifts. Specifically, CUMA enforces the model to have similar generalization ability on the majority and minority groups, by matching the loss curvature distributions of the two groups. We evaluate our method on three popular fairness datasets. Compared with existing methods, CUMA achieves superior fairness under unseen distribution shifts, without sacrificing either the overall accuracy or the in-distribution fairness.

ICLR Conference 2023 Conference Paper

MECTA: Memory-Economic Continual Test-Time Model Adaptation

• Junyuan Hong
• Lingjuan Lyu
• Jiayu Zhou
• Michael Spranger

Continual Test-time Adaptation (CTA) is a promising art to secure accuracy gains in continually-changing environments. The state-of-the-art adaptations improve out-of-distribution model accuracy via computation-efficient online test-time gradient descents but meanwhile cost about times of memory versus the inference, even if only a small portion of parameters are updated. Such high memory consumption of CTA substantially impedes wide applications of advanced CTA on memory-constrained devices. In this paper, we provide a novel solution, dubbed MECTA, to drastically improve the memory efficiency of gradient-based CTA. Our profiling shows that the major memory overhead comes from the intermediate cache for back-propagation, which scales by the batch size, channel, and layer number. Therefore, we propose to reduce batch sizes, adopt an adaptive normalization layer to maintain stable and accurate predictions, and stop the back-propagation caching heuristically. On the other hand, we prune the networks to reduce the computation and memory overheads in optimization and recover the parameters afterward to avoid forgetting. The proposed MECTA is efficient and can be seamlessly plugged into state-of-the-art CTA algorithms at negligible overhead on computation and memory. On three datasets, CIFAR10, CIFAR100, and ImageNet, MECTA improves the accuracy by at least 6% with constrained memory and significantly reduces the memory costs of ResNet50 on ImageNet by at least 70% with comparable accuracy. Our codes can be accessed at https://github.com/SonyAI/MECTA.

ICML Conference 2023 Conference Paper

Revisiting Data-Free Knowledge Distillation with Poisoned Teachers

• Junyuan Hong
• Yi Zeng 0005
• Shuyang Yu
• Lingjuan Lyu
• Ruoxi Jia 0001
• Jiayu Zhou

Data-free knowledge distillation (KD) helps transfer knowledge from a pre-trained model (known as the teacher model) to a smaller model (known as the student model) without access to the original training data used for training the teacher model. However, the security of the synthetic or out-of-distribution (OOD) data required in data-free KD is largely unknown and under-explored. In this work, we make the first effort to uncover the security risk of data-free KD w. r. t. untrusted pre-trained models. We then propose Anti-Backdoor Data-Free KD (ABD), the first plug-in defensive method for data-free KD methods to mitigate the chance of potential backdoors being transferred. We empirically evaluate the effectiveness of our proposed ABD in diminishing transferred backdoor knowledge while maintaining compatible downstream performances as the vanilla KD. We envision this work as a milestone for alarming and mitigating the potential backdoors in data-free KD. Codes are released at https: //github. com/illidanlab/ABD.

ICLR Conference 2023 Conference Paper

Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection

• Shuyang Yu
• Junyuan Hong
• Haotao Wang
• Zhangyang Wang
• Jiayu Zhou

Deep neural networks have witnessed huge successes in many challenging prediction tasks and yet they often suffer from out-of-distribution (OoD) samples, misclassifying them with high confidence. Recent advances show promising OoD detection performance for centralized training, and however, OoD detection in federated learning (FL) is largely overlooked, even though many security sensitive applications such as autonomous driving and voice recognition authorization are commonly trained using FL for data privacy concerns. The main challenge that prevents previous state-of-the-art OoD detection methods from being incorporated to FL is that they require large amount of real OoD samples. However, in real-world scenarios, such large-scale OoD training data can be costly or even infeasible to obtain, especially for resource-limited local devices. On the other hand, a notorious challenge in FL is data heterogeneity where each client collects non-identically and independently distributed (non-iid) data. We propose to take advantage of such heterogeneity and turn the curse into a blessing that facilitates OoD detection in FL. The key is that for each client, non-iid data from other clients (unseen external classes) can serve as an alternative to real OoD samples. Specifically, we propose a novel Federated Out-of-Distribution Synthesizer (FOSTER), which learns a class-conditional generator to synthesize virtual external-class OoD samples, and maintains data confidentiality and communication efficiency required by FL. Experimental results show that our method outperforms the state-of-the-art by 2.49%, 2.88%, 1.42% AUROC, and 0.01%, 0.89%, 1.74% ID accuracy, on CIFAR-10, CIFAR-100, and STL10, respectively.

NeurIPS Conference 2023 Conference Paper

Understanding Deep Gradient Leakage via Inversion Influence Functions

• Haobo Zhang
• Junyuan Hong
• Yuyang Deng
• Mehrdad Mahdavi
• Jiayu Zhou

Deep Gradient Leakage (DGL) is a highly effective attack that recovers private training images from gradient vectors. This attack casts significant privacy challenges on distributed learning from clients with sensitive data, where clients are required to share gradients. Defending against such attacks requires but lacks an understanding of when and how privacy leakage happens, mostly because of the black-box nature of deep networks. In this paper, we propose a novel Inversion Influence Function (I$^2$F) that establishes a closed-form connection between the recovered images and the private gradients by implicitly solving the DGL problem. Compared to directly solving DGL, I$^2$F is scalable for analyzing deep networks, requiring only oracle access to gradients and Jacobian-vector products. We empirically demonstrate that I$^2$F effectively approximated the DGL generally on different model architectures, datasets, modalities, attack implementations, and perturbation-based defenses. With this novel tool, we provide insights into effective gradient perturbation directions, the unfairness of privacy protection, and privacy-preferred model initialization. Our codes are provided in https: //github. com/illidanlab/inversion-influence-function.

AAAI Conference 2023 Conference Paper

USDNL: Uncertainty-Based Single Dropout in Noisy Label Learning

• Yuanzhuo Xu
• Xiaoguang Niu
• Jie Yang
• Steve Drew
• Jiayu Zhou
• Ruizhi Chen

Deep Neural Networks (DNNs) possess powerful prediction capability thanks to their over-parameterization design, although the large model complexity makes it suffer from noisy supervision. Recent approaches seek to eliminate impacts from noisy labels by excluding data points with large loss values and showing promising performance. However, these approaches usually associate with significant computation overhead and lack of theoretical analysis. In this paper, we adopt a perspective to connect label noise with epistemic uncertainty. We design a simple, efficient, and theoretically provable robust algorithm named USDNL for DNNs with uncertainty-based Dropout. Specifically, we estimate the epistemic uncertainty of the network prediction after early training through single Dropout. The epistemic uncertainty is then combined with cross-entropy loss to select the clean samples during training. Finally, we theoretically show the equivalence of replacing selection loss with single cross-entropy loss. Compared to existing small-loss selection methods, USDNL features its simplicity for practical scenarios by only applying Dropout to a standard network, while still achieving high model accuracy. Extensive empirical results on both synthetic and real-world datasets show that USDNL outperforms other methods. Our code is available at https://github.com/kovelxyz/USDNL.

ICLR Conference 2022 Conference Paper

Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization

• Junyuan Hong
• Haotao Wang
• Zhangyang Wang
• Jiayu Zhou

Federated learning (FL) provides a distributed learning framework for multiple participants to collaborate learning without sharing raw data. In many practical FL scenarios, participants have heterogeneous resources due to disparities in hardware and inference dynamics that require quickly loading models of different sizes and levels of robustness. The heterogeneity and dynamics together impose significant challenges to existing FL approaches and thus greatly limit FL's applicability. In this paper, we propose a novel Split-Mix FL strategy for heterogeneous participants that, once training is done, provides in-situ customization of model sizes and robustness. Specifically, we achieve customization by learning a set of base sub-networks of different sizes and robustness levels, which are later aggregated on-demand according to inference requirements. This split-mix strategy achieves customization with high efficiency in communication, storage, and inference. Extensive experiments demonstrate that our method provides better in-situ customization than the existing heterogeneous-architecture FL methods. Codes and pre-trained models are available: https://github.com/illidanlab/SplitMix.

JBHI Journal 2022 Journal Article

Margin Preserving Self-Paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation

• Zhizhe Liu
• Zhenfeng Zhu
• Shuai Zheng
• Yang Liu
• Jiayu Zhou
• Yao Zhao

To bridge the gap between the source and target domains in unsupervised domain adaptation (UDA), the most common strategy puts focus on matching the marginal distributions in the feature space through adversarial learning. However, such category-agnostic global alignment lacks of exploiting the class-level joint distributions, causing the aligned distribution less discriminative. To address this issue, we propose in this paper a novel margin preserving self-paced contrastive Learning (MPSCL) model for cross-modal medical image segmentation. Unlike the conventional construction of contrastive pairs in contrastive learning, the domain-adaptive category prototypes are utilized to constitute the positive and negative sample pairs. With the guidance of progressively refined semantic prototypes, a novel margin preserving contrastive loss is proposed to boost the discriminability of embedded representation space. To enhance the supervision for contrastive learning, more informative pseudo-labels are generated in target domain in a self-paced way, thus benefiting the category-aware distribution alignment for UDA. Furthermore, the domain-invariant representations are learned through joint contrastive learning between the two domains. Extensive experiments on cross-modal cardiac segmentation tasks demonstrate that MPSCL significantly improves semantic segmentation performance, and outperforms a wide variety of state-of-the-art methods by a large margin.

NeurIPS Conference 2022 Conference Paper

Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling

• Junyuan Hong
• Lingjuan Lyu
• Jiayu Zhou
• Michael Spranger

As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and cost-effective end device. Traditional outsourcing requires uploading device data to the cloud server, which can be infeasible in many real-world applications due to the often sensitive nature of the collected data and the limited communication bandwidth. To tackle these challenges, we propose to leverage widely available open-source data, which is a massive dataset collected from public and heterogeneous sources (e. g. , Internet images). We develop a novel strategy called Efficient Collaborative Open-source Sampling (ECOS) to construct a proximal proxy dataset from open-source data for cloud training, in lieu of client data. ECOS probes open-source data on the cloud server to sense the distribution of client data via a communication- and computation-efficient sampling process, which only communicates a few compressed public features and client scalar responses. Extensive empirical studies show that the proposed ECOS improves the quality of automated client labeling, model compression, and label outsourcing when applied in various learning scenarios. Source codes will be released.

ICML Conference 2022 Conference Paper

Resilient and Communication Efficient Learning for Heterogeneous Federated Systems

• Zhuangdi Zhu
• Junyuan Hong
• Steve Drew 0001
• Jiayu Zhou

The rise of Federated Learning (FL) is bringing machine learning to edge computing by utilizing data scattered across edge devices. However, the heterogeneity of edge network topologies and the uncertainty of wireless transmission are two major obstructions of FL’s wide application in edge computing, leading to prohibitive convergence time and high communication cost. In this work, we propose an FL scheme to address both challenges simultaneously. Specifically, we enable edge devices to learn self-distilled neural networks that are readily prunable to arbitrary sizes, which capture the knowledge of the learning domain in a nested and progressive manner. Not only does our approach tackle system heterogeneity by serving edge devices with varying model architectures, but it also alleviates the issue of connection uncertainty by allowing transmitting part of the model parameters under faulty network connections, without wasting the contributing knowledge of the transmitted parameters. Extensive empirical studies show that under system heterogeneity and network instability, our approach demonstrates significant resilience and higher communication efficiency compared to the state-of-the-art.

AAAI Conference 2022 Conference Paper

Self-Adaptive Imitation Learning: Learning Tasks with Delayed Rewards from Sub-optimal Demonstrations

• Zhuangdi Zhu
• Kaixiang Lin
• Bo Dai
• Jiayu Zhou

Reinforcement learning (RL) has demonstrated its superiority in solving sequential decision-making problems. However, heavy dependence on immediate reward feedback impedes the wide application of RL. On the other hand, imitation learning (IL) tackles RL without relying on environmental supervision by leveraging external demonstrations. In practice, however, collecting sufficient expert demonstrations can be prohibitively expensive, yet the quality of demonstrations typically limits the performance of the learning policy. To address a practical scenario, in this work, we propose Self- Adaptive Imitation Learning (SAIL), which, provided with a few demonstrations from a sub-optimal teacher, can perform well in RL tasks with extremely delayed rewards, where the only reward feedback is trajectory-wise ranking. SAIL bridges the advantages of IL and RL by interactively exploiting the demonstrations to catch up with the teacher and exploring the environment to yield demonstrations that surpass the teacher. Extensive empirical results show that not only does SAIL significantly improve the sample efficiency, but it also leads to higher asymptotic performance across different continuous control tasks, compared with the state-of-the-art.

NeurIPS Conference 2022 Conference Paper

Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork

• Haotao Wang
• Junyuan Hong
• Aston Zhang
• Jiayu Zhou
• Zhangyang Wang

Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can be affected by the backdoor samples. In this paper, we propose a brand-new backdoor defense strategy, which makes it much easier to remove the harmful influence of backdoor samples from the model. Our defense strategy, \emph{Trap and Replace}, consists of two stages. In the first stage, we bait and trap the backdoors in a small and easy-to-replace subnetwork. Specifically, we add an auxiliary image reconstruction head on top of the stem network shared with a light-weighted classification head. The intuition is that the auxiliary image reconstruction task encourages the stem network to keep sufficient low-level visual features that are hard to learn but semantically correct, instead of overfitting to the easy-to-learn but semantically incorrect backdoor correlations. As a result, when trained on backdoored datasets, the backdoors are easily baited towards the unprotected classification head, since it is much more vulnerable than the shared stem, leaving the stem network hardly poisoned. In the second stage, we replace the poisoned light-weighted classification head with an untainted one, by re-training it from scratch only on a small holdout dataset with clean samples, while fixing the stem network. As a result, both the stem and the classification head in the final network are hardly affected by backdoor training samples. We evaluate our method against ten different backdoor attacks. Our method outperforms previous state-of-the-art methods by up to $20. 57\%$, $9. 80\%$, and $13. 72\%$ attack success rate and on-average $3. 14\%$, $1. 80\%$, and $1. 21\%$ clean classification accuracy on CIFAR10, GTSRB, and ImageNet-12, respectively. Code is available at https: //github. com/VITA-Group/Trap-and-Replace-Backdoor-Defense.

AAAI Conference 2022 Conference Paper

Unsupervised Anomaly Detection by Robust Density Estimation

• Boyang Liu
• Pang-Ning Tan
• Jiayu Zhou

Density estimation is a widely used method for unsupervised anomaly detection. However, the presence of anomalies in training data may severely impact the density estimation process, thereby hampering the use of more sophisticated density estimation methods such as those based on deep neural networks. In this work, we propose RobustRealNVP, a robust deep density estimation framework for unsupervised anomaly detection. Our approach differs from existing flowbased models from two perspectives. First, RobustRealNVP discards data points with low estimated densities during optimization to prevent them from corrupting the density estimation process. Furthermore, it imposes Lipschitz regularization to ensure smoothness in the estimated density function. We demonstrate the robustness of our algorithm against anomalies in training data from both theoretical and empirical perspectives. The results show that our algorithm outperforms state-of-the-art unsupervised anomaly detection methods.

ICML Conference 2021 Conference Paper

Data-Free Knowledge Distillation for Heterogeneous Federated Learning

• Zhuangdi Zhu
• Junyuan Hong
• Jiayu Zhou

Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data. User heterogeneity has imposed significant challenges to FL, which can incur drifted global models that are slow to converge. Knowledge Distillation has recently emerged to tackle this issue, by refining the server model using aggregated knowledge from heterogeneous users, other than directly averaging their model parameters. This approach, however, depends on a proxy dataset, making it impractical unless such a prerequisite is satisfied. Moreover, the ensemble knowledge is not fully utilized to guide local model learning, which may in turn affect the quality of the aggregated model. Inspired by the prior art, we propose a data-free knowledge distillation approach to address heterogeneous FL, where the server learns a lightweight generator to ensemble user information in a data-free manner, which is then broadcasted to users, regulating local training using the learned knowledge as an inductive bias. Empirical studies powered by theoretical implications show that our approach facilitates FL with better generalization performance using fewer communication rounds, compared with the state-of-the-art.

ICML Conference 2021 Conference Paper

Learning Deep Neural Networks under Agnostic Corrupted Supervision

• Boyang Liu
• Mengying Sun
• Ding Wang
• Pang-Ning Tan
• Jiayu Zhou

Training deep neural network models in the presence of corrupted supervision is challenging as the corrupted data points may significantly impact generalization performance. To alleviate this problem, we present an efficient robust algorithm that achieves strong guarantees without any assumption on the type of corruption and provides a unified framework for both classification and regression problems. Unlike many existing approaches that quantify the quality of the data points (e. g. , based on their individual loss values), and filter them accordingly, the proposed algorithm focuses on controlling the collective impact of data points on the average gradient. Even when a corrupted data point failed to be excluded by our algorithm, the data point will have a very limited impact on the overall loss, as compared with state-of-the-art filtering methods based on loss values. Extensive experiments on multiple benchmark datasets have demonstrated the robustness of our algorithm under different types of corruption. Our code is available at \url{https: //github. com/illidanlab/PRL}.

AAAI Conference 2021 Conference Paper

Learning Model-Based Privacy Protection under Budget Constraints

• Junyuan Hong
• Haotao Wang
• Zhangyang Wang
• Jiayu Zhou

Protecting privacy in gradient-based learning has become increasingly critical as more sensitive information is being used. Many existing solutions seek to protect the sensitive gradients by constraining the overall privacy cost within a constant budget, where the protection is hand-designed and empirically calibrated to boost the utility of the resulting model. However, it remains challenging to choose the proper protection adapted for specific constraints so that the utility is maximized. To this end, we propose a novel Learning-to-Protect algorithm that automatically learns a model-based protector from a set of nonprivate learning tasks. The learned protector can be applied to private learning tasks to improve utility within the specific privacy budget constraint. Our empirical studies on both synthetic and real datasets demonstrate that the proposed algorithm can achieve a superior utility with a given privacy constraint and generalize well to new private datasets distributed differently as compared to the hand-designed competitors.

IJCAI Conference 2021 Conference Paper

RCA: A Deep Collaborative Autoencoder Approach for Anomaly Detection

• Boyang Liu
• Ding Wang
• Kaixiang Lin
• Pang-Ning Tan
• Jiayu Zhou

Unsupervised anomaly detection plays a crucial role in many critical applications. Driven by the success of deep learning, recent years have witnessed growing interests in applying deep neural networks (DNNs) to anomaly detection problems. A common approach is using autoencoders to learn a feature representation for the normal observations in the data. The reconstruction error of the autoencoder is then used as outlier scores to detect the anomalies. However, due to the high complexity brought upon by the over-parameterization of DNNs, the reconstruction error of the anomalies could also be small, which hampers the effectiveness of these methods. To alleviate this problem, we propose a robust framework using collaborative autoencoders to jointly identify normal observations from the data while learning its feature representation. We investigate the theoretical properties of the framework and empirically show its outstanding performance as compared to other DNN-based methods. Our experimental results also show the resiliency of the framework to missing values compared to other baseline methods.

NeurIPS Conference 2020 Conference Paper

Off-Policy Imitation Learning from Observations

• Zhuangdi Zhu
• Kaixiang Lin
• Bo Dai
• Jiayu Zhou

Learning from Observations (LfO) is a practical reinforcement learning scenario from which many applications can benefit through the reuse of incomplete resources. Compared to conventional imitation learning (IL), LfO is more challenging because of the lack of expert action guidance. In both conventional IL and LfO, distribution matching is at the heart of their foundation. Traditional distribution matching approaches are sample-costly which depend on on-policy transitions for policy learning. Towards sample-efficiency, some off-policy solutions have been proposed, which, however, either lack comprehensive theoretical justifications or depend on the guidance of expert actions. In this work, we propose a sample-efficient LfO approach which enables off-policy optimization in a principled manner. To further accelerate the learning procedure, we regulate the policy update with an inverse action model, which assists distribution matching from the perspective of mode-covering. Extensive empirical results on challenging locomotion tasks indicate that our approach is comparable with state-of-the-art in terms of both sample-efficiency and asymptotic performance.

ICLR Conference 2020 Conference Paper

Ranking Policy Gradient

• Kaixiang Lin
• Jiayu Zhou

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization. Towards the sample-efficient RL, we propose ranking policy gradient (RPG), a policy gradient method that learns the optimal rank of a set of discrete actions. To accelerate the learning of policy gradient methods, we establish the equivalence between maximizing the lower bound of return and imitating a near-optimal policy without accessing any oracles. These results lead to a general off-policy learning framework, which preserves the optimality, reduces variance, and improves the sample-efficiency. We conduct extensive experiments showing that when consolidating with the off-policy learning framework, RPG substantially reduces the sample complexity, comparing to the state-of-the-art.

AAAI Conference 2020 Conference Paper

Shoreline: Data-Driven Threshold Estimation of Online Reserves of Cryptocurrency Trading Platforms

• Xitong Zhang
• He Zhu
• Jiayu Zhou

With the proliferation of blockchain projects and applications, cryptocurrency exchanges, which provides exchange services among different types of cryptocurrencies, become pivotal platforms that allow customers to trade digital assets on different blockchains. Because of the anonymity and trustlessness nature of cryptocurrency, one major challenge of crypto-exchanges is asset safety, and all-time amount hacked from crypto-exchanges until 2018 is over $1. 5 billion even with carefully maintained secure trading systems. The most critical vulnerability of crypto-exchanges is from the socalled hot wallet, which is used to store a certain portion of the total asset of an exchange and programmatically sign transactions when a withdraw happens. Whenever hackers managed to gain control over the computing infrastructure of the exchange, they usually immediately obtain all the assets in the hot wallet. It is important to develop network security mechanisms. However, the fact is that there is no guarantee that the system can defend all attacks. Thus, accurately controlling the available assets in the hot wallets becomes the key to minimize the risk of running an exchange. However, determining such optimal threshold remains a challenging task because of the complicated dynamics inside exchanges. In this paper, we propose SHORELINE, a deep learning-based threshold estimation framework that estimates the optimal threshold of hot wallets from historical wallet activities and dynamic trading networks. We conduct extensive empirical studies on the real trading data from a trading platform and demonstrate the effectiveness of the proposed approach.

AAAI Conference 2020 Short Paper

Shoreline: Data-Driven Threshold Estimation of Online Reserves of Cryptocurrency Trading Platforms (Student Abstract)

• Xitong Zhang
• He Zhu
• Jiayu Zhou

With the proliferation of blockchain projects and applications, cryptocurrency exchanges, which provides exchange services among different types of cryptocurrencies, become pivotal platforms that allow customers to trade digital assets on different blockchains. Because of the anonymity and trustlessness nature of cryptocurrency, one major challenge of crypto-exchanges is asset safety, and all-time amount hacked from crypto-exchanges until 2018 is over $1. 5 billion even with carefully maintained secure trading systems. The most critical vulnerability of crypto-exchanges is from the socalled hot wallet, which is used to store a certain portion of the total asset online of an exchange and programmatically sign transactions when a withdraw happens. It is important to develop network security mechanisms. However, the fact is that there is no guarantee that the system can defend all attacks. Thus, accurately controlling the available assets in the hot wallets becomes the key to minimize the risk of running an exchange. In this paper, we propose SHORELINE, a deep learning-based threshold estimation framework that estimates the optimal threshold of hot wallets from historical wallet activities and dynamic trading networks.

AAAI Conference 2020 Short Paper

Structure-Based Drug-Drug Interaction Detection via Expressive Graph Convolutional Networks and Deep Sets (Student Abstract)

• Mengying Sun
• Fei Wang
• Olivier Elemento
• Jiayu Zhou

In this work, we proposed a DDI detection method based on molecular structures using graph convolutional networks and deep sets. We proposed a more discriminative convolutional layer compared to conventional GCN and achieved permutation invariant prediction without losing the capability of capturing complicated interactions.

AAAI Conference 2019 Conference Paper

Confidence Weighted Multitask Learning

• Peng Yang
• Peilin Zhao
• Jiayu Zhou
• Xin Gao

Traditional online multitask learning only utilizes the firstorder information of the datastream. To remedy this issue, we propose a confidence weighted multitask learning algorithm, which maintains a Gaussian distribution over each task model to guide online learning process. The mean (covariance) of the Gaussian Distribution is a sum of a local component and a global component that is shared among all the tasks. In addition, this paper also addresses the challenge of active learning on the online multitask setting. Instead of requiring labels of all the instances, the proposed algorithm determines whether the learner should acquire a label by considering the confidence from its related tasks over label prediction. Theoretical results show the regret bounds can be significantly reduced. Empirical results demonstrate that the proposed algorithm is able to achieve promising learning efficacy, while simultaneously minimizing the labeling cost.

NeurIPS Conference 2018 Conference Paper

Boosted Sparse and Low-Rank Tensor Regression

• Lifang He
• Kun Chen
• Wanwan Xu
• Jiayu Zhou
• Fei Wang

We propose a sparse and low-rank tensor regression model to relate a univariate outcome to a feature tensor, in which each unit-rank tensor from the CP decomposition of the coefficient tensor is assumed to be sparse. This structure is both parsimonious and highly interpretable, as it implies that the outcome is related to the features through a few distinct pathways, each of which may only involve subsets of feature dimensions. We take a divide-and-conquer strategy to simplify the task into a set of sparse unit-rank tensor regression problems. To make the computation efficient and scalable, for the unit-rank tensor regression, we propose a stagewise estimation procedure to efficiently trace out its entire solution path. We show that as the step size goes to zero, the stagewise solution paths converge exactly to those of the corresponding regularized regression. The superior performance of our approach is demonstrated on various real-world and synthetic examples.

IJCAI Conference 2018 Conference Paper

Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders

• Tengfei Ma
• Cao Xiao
• Jiayu Zhou
• Fei Wang

Drug similarity has been studied to support downstream clinical tasks such as inferring novel properties of drugs (e. g. side effects, indications, interactions) from known properties. The growing availability of new types of drug features brings the opportunity of learning a more comprehensive and accurate drug similarity that represents the full spectrum of underlying drug relations. However, it is challenging to integrate these heterogeneous, noisy, nonlinear-related information to learn accurate similarity measures especially when labels are scarce. Moreover, there is a trade-off between accuracy and interpretability. In this paper, we propose to learn accurate and interpretable similarity measures from multiple types of drug features. In particular, we model the integration using multi-view graph auto-encoders, and add attentive mechanism to determine the weights for each view with respect to corresponding tasks and features for better interpretability. Our model has flexible design for both semi-supervised and unsupervised settings. Experimental results demonstrated significant predictive accuracy improvement. Case studies also showed better model capacity (e. g. embed node features) and interpretability.

IJCAI Conference 2017 Conference Paper

Doubly Sparsifying Network

• Zhangyang Wang
• Shuai Huang
• Jiayu Zhou
• Thomas S. Huang

We propose the doubly sparsifying network (DSN), by drawing inspirations from the double sparsity model for dictionary learning. DSN emphasizes the joint utilization of both the problem structure and the parameter structure. It simultaneously sparsifies the output features and the learned model parameters, under one unified framework. DSN enjoys intuitive model interpretation, compact model size and low complexity. We compare DSN against a few carefully-designed baselines, to verify its consistently superior performance in a wide range of settings. Encouraged by its robustness to insufficient training data, we explore the applicability of DSN in brain signal processing that has been a challenging interdisciplinary area. DSN is evaluated for two mainstream tasks, electroencephalographic (EEG) signal classification and blood oxygenation level dependent (BOLD) response prediction, both achieving promising results.

IJCAI Conference 2015 Conference Paper

A Space Alignment Method for Cold-Start TV Show Recommendations

• Shiyu Chang
• Jiayu Zhou
• Pirooz Chubak
• Junling Hu
• Thomas Huang

In recent years, recommendation algorithms have become one of the most active research areas driven by the enormous industrial demands. Most of the existing recommender systems focus on topics such as movie, music, e-commerce etc. , which essentially differ from the TV show recommendations due to the cold-start and temporal dynamics. Both effectiveness (effectively handling the cold-start TV shows) and efficiency (efficiently updating the model to reflect the temporal data changes) concerns have to be addressed to design real-world TV show recommendation algorithms. In this paper, we introduce a novel hybrid recommendation algorithm incorporating both collaborative user-item relationship as well as item content features. The cold-start TV shows can be correctly recommended to desired users via a so called space alignment technique. On the other hand, an online updating scheme is developed to utilize new user watching behaviors. We present experimental results on a real TV watch behavior data set to demonstrate the significant performance improvement over other state-of-the-art algorithms.

NeurIPS Conference 2014 Conference Paper

A Safe Screening Rule for Sparse Logistic Regression

• Jie Wang
• Jiayu Zhou
• Jun Liu
• Peter Wonka
• Jieping Ye

The l1-regularized logistic regression (or sparse logistic regression) is a widely used method for simultaneous classification and feature selection. Although many recent efforts have been devoted to its efficient implementation, its application to high dimensional data still poses significant challenges. In this paper, we present a fast and effective sparse logistic regression screening rule (Slores) to identify the zero components in the solution vector, which may lead to a substantial reduction in the number of features to be entered to the optimization. An appealing feature of Slores is that the data set needs to be scanned only once to run the screening and its computational cost is negligible compared to that of solving the sparse logistic regression problem. Moreover, Slores is independent of solvers for sparse logistic regression, thus Slores can be integrated with any existing solver to improve the efficiency. We have evaluated Slores using high-dimensional data sets from different applications. Extensive experimental results demonstrate that Slores outperforms the existing state-of-the-art screening rules and the efficiency of solving sparse logistic regression is improved by one magnitude in general.

YNIMG Journal 2014 Journal Article

Analysis of sampling techniques for imbalanced data: An n = 648 ADNI study

• Rashmi Dubey
• Jiayu Zhou
• Yalin Wang
• Paul M. Thompson
• Jieping Ye

NeurIPS Conference 2013 Conference Paper

Lasso Screening Rules via Dual Polytope Projection

• Jie Wang
• Jiayu Zhou
• Peter Wonka
• Jieping Ye

Lasso is a widely used regression technique to find sparse representations. When the dimension of the feature space and the number of samples are extremely large, solving the Lasso problem remains challenging. To improve the efficiency of solving large-scale Lasso problems, El Ghaoui and his colleagues have proposed the SAFE rules which are able to quickly identify the inactive predictors, i. e. , predictors that have $0$ components in the solution vector. Then, the inactive predictors or features can be removed from the optimization problem to reduce its scale. By transforming the standard Lasso to its dual form, it can be shown that the inactive predictors include the set of inactive constraints on the optimal dual solution. In this paper, we propose an efficient and effective screening rule via Dual Polytope Projections (DPP), which is mainly based on the uniqueness and nonexpansiveness of the optimal dual solution due to the fact that the feasible set in the dual space is a convex and closed polytope. Moreover, we show that our screening rule can be extended to identify inactive groups in group Lasso. To the best of our knowledge, there is currently no exact" screening rule for group Lasso. We have evaluated our screening rule using many real data sets. Results show that our rule is more effective to identify inactive predictors than existing state-of-the-art screening rules for Lasso. "

YNIMG Journal 2013 Journal Article

Modeling disease progression via multi-task learning

• Jiayu Zhou
• Jun Liu
• Vaibhav A. Narayan
• Jieping Ye

NeurIPS Conference 2011 Conference Paper

Clustered Multi-Task Learning Via Alternating Structure Optimization

• Jiayu Zhou
• Jianhui Chen
• Jieping Ye

Multi-task learning (MTL) learns multiple related tasks simultaneously to improve generalization performance. Alternating structure optimization (ASO) is a popular MTL method that learns a shared low-dimensional predictive structure on hypothesis spaces from multiple related tasks. It has been applied successfully in many real world applications. As an alternative MTL approach, clustered multi-task learning (CMTL) assumes that multiple tasks follow a clustered structure, i. e. , tasks are partitioned into a set of groups where tasks in the same group are similar to each other, and that such a clustered structure is unknown a priori. The objectives in ASO and CMTL differ in how multiple tasks are related. Interestingly, we show in this paper the equivalence relationship between ASO and CMTL, providing significant new insights into ASO and CMTL as well as their inherent relationship. The CMTL formulation is non-convex, and we adopt a convex relaxation to the CMTL formulation. We further establish the equivalence relationship between the proposed convex relaxation of CMTL and an existing convex relaxation of ASO, and show that the proposed convex CMTL formulation is significantly more efficient especially for high-dimensional data. In addition, we present three algorithms for solving the convex CMTL formulation. We report experimental results on benchmark datasets to demonstrate the efficiency of the proposed algorithms.

AAAI Conference 2008 Short Paper

Visualization of Large-Scale Weighted Clustered Graph: A Genetic Approach

• Jiayu Zhou

In this paper, a bottom-up hierarchical genetic algorithm is proposed to visualize clustered data into a planar graph. To achieve global optimization by accelerating local optimization process, we introduce subgraph rotating and scaling processes into the genetic algorithm. Compared with existing methods, the proposed approach is more feasible and promising, with more accurate graph layout and more satisfiable computationally efficient performance, as demonstrated by the experimental results.