Xinwang Liu

Learning Vector-valued Functions with Local Rademacher Complexity and Unlabeled Data

2019 · arXiv (Cornell University)

We consider a general family of problems of which the output space admits vector-valued structure, covering a broad family of important domains, e.g. multi-label learning and multi-class classification. By using local Rademacher complexity and unlabeled …

RARE: Robust Masked Graph Autoencoder

2023 · arXiv (Cornell University)

Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data space as is done …

Cluster-Guided Contrastive Graph Clustering Network

2023 · Proceedings of the AAAI Conference on Artificial Intelligence

Benefiting from the intrinsic supervision information exploitation capability, contrastive learning has achieved promising performance in the field of deep graph clustering recently. However, we observe that two drawbacks of the positive and negative sample construction …

RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization

2023 · arXiv (Cornell University)

Multi-agent systems are characterized by environmental uncertainty, varying policies of agents, and partial observability, which result in significant risks. In the context of Multi-Agent Reinforcement Learning (MARL), learning coordinated and decentralized policies that are sensitive …