5 papers
Offline Multi-agent Reinforcement Learning via Sequential Score Decomposition
Dan Qiao, Wenhao Li, Shanchao Yang +2
Offline cooperative multi-agent reinforcement learning (MARL) faces unique challenges due to distributional shifts, particularly stemming from the high dimensionality of joint acti…
Revisiting the Auxiliary Data in Backdoor Purification
Shaokui Wei, Shanchao Yang, Jiayin Liu +1
Backdoor attacks occur when an attacker subtly manipulates machine learning models during the training phase, leading to unintended behaviors when specific triggers are present. To…
Diverse Policy Optimization for Structured Action Space
Wenhao Li, Baoxiang Wang, Shanchao Yang +1
Enhancing the diversity of policies is beneficial for robustness, exploration, and transfer in reinforcement learning (RL). In this paper, we aim to seek diverse policies in an und…
Edge Rewiring Goes Neural: Boosting Network Resilience without Rich Features
Shanchao Yang, Kaili Ma, Baoxiang Wang +2
Improving the resilience of a network is a fundamental problem in network science, which protects the underlying system from natural disasters and malicious attacks. This is tradit…
Learning to Generate Time Series Conditioned Graphs with Generative Adversarial Nets
Shanchao Yang, Jing Liu, Kai Wu +1
Deep learning based approaches have been utilized to model and generate graphs subjected to different distributions recently. However, they are typically unsupervised learning base…