Author name cluster

Jing Jiang 0002

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

ICML Conference 2023 Conference Paper

Continual Task Allocation in Meta-Policy Network via Sparse Prompting

Yijun Yang
Tianyi Zhou 0001
Jing Jiang 0002
Guodong Long
Yuhui Shi 0001

How to train a generalizable meta-policy by continually learning a sequence of tasks? It is a natural human skill yet challenging to achieve by current reinforcement learning: the agent is expected to quickly adapt to new tasks (plasticity) meanwhile retaining the common knowledge from previous tasks (stability). We address it by "Continual Task Allocation via Sparse Prompting (CoTASP)", which learns over-complete dictionaries to produce sparse masks as prompts extracting a sub-network for each task from a meta-policy network. CoTASP trains a policy for each task by optimizing the prompts and the sub-network weights alternatively. The dictionary is then updated to align the optimized prompts with tasks’ embedding, thereby capturing tasks’ semantic correlations. Hence, relevant tasks share more neurons in the meta-policy network due to similar prompts while cross-task interference causing forgetting is effectively restrained. Given a meta-policy and dictionaries trained on previous tasks, new task adaptation reduces to highly efficient sparse prompting and sub-network finetuning. In experiments, CoTASP achieves a promising plasticity-stability trade-off without storing or replaying any past tasks’ experiences. It outperforms existing continual and multi-task RL methods on all seen tasks, forgetting reduction, and generalization to unseen tasks.

Details

ICML Conference 2023 Conference Paper

Does Continual Learning Equally Forget All Parameters?

Haiyan Zhao
Tianyi Zhou 0001
Guodong Long
Jing Jiang 0002
Chengqi Zhang

Distribution shift (e. g. , task or domain shift) in continual learning (CL) usually results in catastrophic forgetting of previously learned knowledge. Although it can be alleviated by repeatedly replaying buffered data, the every-step replay is time-consuming. In this paper, we study which modules in neural networks are more prone to forgetting by investigating their training dynamics during CL. Our proposed metrics show that only a few modules are more task-specific and sensitive to task change, while others can be shared across tasks as common knowledge. Hence, we attribute forgetting mainly to the former and find that finetuning them only on a small buffer at the end of any CL method can bring non-trivial improvement. Due to the small number of finetuned parameters, such ”Forgetting Prioritized Finetuning (FPF)” is efficient in computation. We further propose a more efficient and simpler method that entirely removes the every-step replay and replaces them by only $k$-times of FPF periodically triggered during CL. Surprisingly, this ”$k$-FPF” performs comparably to FPF and outperforms the SOTA CL methods but significantly reduces their computational overhead and cost. In experiments on several benchmarks of class- and domain-incremental CL, FPF consistently improves existing CL methods by a large margin, and $k$-FPF further excels in efficiency without degrading the accuracy. We also empirically studied the impact of buffer size, epochs per task, and finetuning modules on the cost and accuracy of our methods.

Details

ICML Conference 2022 Conference Paper

EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning

Shuang Ao
Tianyi Zhou 0001
Jing Jiang 0002
Guodong Long
Xuan Song 0001
Chengqi Zhang

Reinforcement learning (RL) is inefficient on long-horizon tasks due to sparse rewards and its policy can be fragile to slightly perturbed environments. We address these challenges via a curriculum of tasks with coupled environments, generated by two policies trained jointly with RL: (1) a co-operative planning policy recursively decomposing a hard task into a coarse-to-fine sub-task tree; and (2) an adversarial policy modifying the environment in each sub-task. They are complementary to acquire more informative feedback for RL: (1) provides dense reward of easier sub-tasks while (2) modifies sub-tasks’ environments to be more challenging and diverse. Conversely, they are trained by RL’s dense feedback on sub-tasks so their generated curriculum keeps adaptive to RL’s progress. The sub-task tree enables an easy-to-hard curriculum for every policy: its top-down construction gradually increases sub-tasks the planner needs to generate, while the adversarial training between the environment and RL follows a bottom-up traversal that starts from a dense sequence of easier sub-tasks allowing more frequent environment changes. We compare EAT-C with RL/planning targeting similar problems and methods with environment generators or adversarial agents. Extensive experiments on diverse tasks demonstrate the advantages of our method on improving RL’s efficiency and generalization.

Details

ICLR Conference 2022 Conference Paper

Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification

Wensi Tang
Guodong Long
Lu Liu 0019
Tianyi Zhou 0001
Michael Blumenstein
Jing Jiang 0002

The size of the receptive field has been one of the most important factors for One Dimensional Convolutional Neural Networks (1D-CNNs) on time series classification tasks. Large efforts have been taken to choose the appropriate receptive field size, for it has a huge influence on the performance and differs significantly for each dataset. In this paper, we propose an Omni-Scale block (OS-block) for 1D-CNNs, where the kernel sizes are set by a simple and universal rule. OS-block can efficiently cover the best size of the receptive field across different datasets. This set of kernel sizes consists of multiple prime numbers according to the length of the time series. We experimentally show 1D-CNNs built from OS-block can consistently achieve the state-of-the-art accuracy with a smaller model size on five time series benchmarks, including both univariate and multivariate data from multiple domains. Comprehensive analysis and ablation studies shed light on how our rule finds the best receptive field size and demonstrate the consistency of our OS-block for multiple 1D-CNN structures.

Details

ICLR Conference 2022 Conference Paper

Pareto Policy Pool for Model-based Offline Reinforcement Learning

Yijun Yang
Jing Jiang 0002
Tianyi Zhou 0001
Jie Ma
Yuhui Shi 0001

Online reinforcement learning (RL) can suffer from poor exploration, sparse reward, insufficient data, and overhead caused by inefficient interactions between an immature policy and a complicated environment. Model-based offline RL instead trains an environment model using a dataset of pre-collected experiences so online RL methods can learn in an offline manner by solely interacting with the model. However, the uncertainty and accuracy of the environment model can drastically vary across different state-action pairs so the RL agent may achieve high model return but perform poorly in the true environment. Unlike previous works that need to carefully tune the trade-off between the model return and uncertainty in a single objective, we study a bi-objective formulation for model-based offline RL that aims at producing a pool of diverse policies on the Pareto front performing different levels of trade-offs, which provides the flexibility to select the best policy for each realistic environment from the pool. Our method, ''Pareto policy pool (P3)'', does not need to tune the trade-off weight but can produce policies allocated at different regions of the Pareto front. For this purpose, we develop an efficient algorithm that solves multiple bi-objective optimization problems with distinct constraints defined by reference vectors targeting diverse regions of the Pareto front. We theoretically prove that our algorithm can converge to the targeted regions. In order to obtain more Pareto optimal policies without linearly increasing the cost, we leverage the achieved policies as initialization to find more Pareto optimal policies in their neighborhoods. On the D4RL benchmark for offline RL, P3 substantially outperforms several recent baseline methods over multiple tasks, especially when the quality of pre-collected experiences is low.

Details

ICLR Conference 2021 Conference Paper

A Universal Representation Transformer Layer for Few-Shot Image Classification

Lu Liu 0019
William L. Hamilton
Guodong Long
Jing Jiang 0002
Hugo Larochelle

Few-shot classification aims to recognize unseen classes when presented with only a small number of samples. We consider the problem of multi-domain few-shot image classification, where unseen classes and examples come from diverse data sources. This problem has seen growing interest and has inspired the development of benchmarks such as Meta-Dataset. A key challenge in this multi-domain setting is to effectively integrate the feature representations from the diverse set of training domains. Here, we propose a Universal Representation Transformer (URT) layer, that meta-learns to leverage universal features for few-shot classification by dynamically re-weighting and composing the most appropriate domain-specific representations. In experiments, we show that URT sets a new state-of-the-art result on Meta-Dataset. Specifically, it achieves top-performance on the highest number of data sources compared to competing methods. We analyze variants of URT and present a visualization of the attention score heatmaps that sheds light on how the model performs cross-domain generalization.

Details

ICLR Conference 2021 Conference Paper

Isometric Propagation Network for Generalized Zero-shot Learning

Lu Liu 0019
Tianyi Zhou 0001
Guodong Long
Jing Jiang 0002
Xuanyi Dong
Chengqi Zhang

Zero-shot learning (ZSL) aims to classify images of an unseen class only based on a few attributes describing that class but no access to any training sample. A popular strategy is to learn a mapping between the semantic space of class attributes and the visual space of images based on the seen classes and their data. Thus, an unseen class image can be ideally mapped to its corresponding class attributes. The key challenge is how to align the representations in the two spaces. For most ZSL settings, the attributes for each seen/unseen class are only represented by a vector while the seen-class data provide much more information. Thus, the imbalanced supervision from the semantic and the visual space can make the learned mapping easily overfitting to the seen classes. To resolve this problem, we propose Isometric Propagation Network (IPN), which learns to strengthen the relation between classes within each space and align the class dependency in the two spaces. Specifically, IPN learns to propagate the class representations on an auto-generated graph within each space. In contrast to only aligning the resulted static representation, we regularize the two dynamic propagation procedures to be isometric in terms of the two graphs' edge weights per step by minimizing a consistency loss between them. IPN achieves state-of-the-art performance on three popular ZSL benchmarks. To evaluate the generalization capability of IPN, we further build two larger benchmarks with more diverse unseen classes and demonstrate the advantages of IPN on them.

Details