63 citations · 319 across the 19 of their papers we have counts for
10 papers · 1 filter
Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities
Jianda Chen, Sinno Jialin Pan
How to learn an effective reinforcement learning-based model for control tasks from high-level visual observations is a practical and challenging problem. A key to solving this pro…
Fast Graph Generation via Spectral Diffusion
Tianze Luo, Zhanfeng Mo, Sinno Jialin Pan
Generating graph-structured data is a challenging problem, which requires learning the underlying distribution of graphs. Various models such as graph VAE, graph GANs, and graph di…
Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization
Danni Peng, Sinno Jialin Pan
To address distribution shifts between training and test data, domain generalization (DG) leverages multiple source domains to learn a model that generalizes well to unseen domains…
AdaRNN: Adaptive Learning and Forecasting of Time Series
Yuntao Du, Jindong Wang, Wenjie Feng +4
Time series has wide applications in the real world and is known to be difficult to forecast. Since its statistical properties change over time, its distribution also changes tempo…
Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions
Tianbo Li, Tianze Luo, Yiping Ke +1
Attributed event sequences are commonly encountered in practice. A recent research line focuses on incorporating neural networks with the statistical model -- marked point processe…
Reinforcement Learning with Efficient Active Feature Acquisition
Haiyan Yin, Yingzhen Li, Sinno Jialin Pan +2
Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem. To be successful, an agent needs to efficiently gath…
Transfer Value Iteration Networks
Junyi Shen, Hankz Hankui Zhuo, Jin Xu +2
Value iteration networks (VINs) have been demonstrated to have a good generalization ability for reinforcement learning tasks across similar domains. However, based on our experime…
Hashing over Predicted Future Frames for Informed Exploration of Deep Reinforcement Learning
Haiyan Yin, Jianda Chen, Sinno Jialin Pan
In deep reinforcement learning (RL) tasks, an efficient exploration mechanism should be able to encourage an agent to take actions that lead to less frequent states which may yield…
Distributed Multi-Task Relationship Learning
Sulin Liu, Sinno Jialin Pan, Qirong Ho
Multi-task learning aims to learn multiple tasks jointly by exploiting their relatedness to improve the generalization performance for each task. Traditionally, to perform multi-ta…
Transfer Hashing with Privileged Information
Joey Tianyi Zhou, Xinxing Xu, Sinno Jialin Pan +3
Most existing learning to hash methods assume that there are sufficient data, either labeled or unlabeled, on the domain of interest (i.e., the target domain) for training. However…