4 papers
Rethinking Graph Out-Of-Distribution Generalization: A Learnable Random Walk Perspective
Henan Sun, Xunkai Li, Lei Zhu +4
Out-Of-Distribution (OOD) generalization has gained increasing attentions for machine learning on graphs, as graph neural networks (GNNs) often exhibit performance degradation unde…
LLaTA: Unlocking Graph Structure Learning with Tree-Guided Large Language Models
Zhihan Zhang, Xunkai Li, Lei Zhu +6
The emergence of large language models (LLMs) has popularized text-attributed graphs (TAGs), creating an urgent need for graph structure learning (GSL) methods that effectively lev…
Dynamic Backtracking in GFlowNets: Enhancing Decision Steps with Reward-Dependent Adjustment Mechanisms
Shuai Guo, Jielei Chu, Lin Ma +2
Generative Flow Networks (GFlowNets or GFNs) are probabilistic models predicated on Markov flows, and they employ specific amortization algorithms to learn stochastic policies that…
GSINA: Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attention
Junchi Yan, Fangyu Ding, Jiawei Sun +3
Graph invariant learning (GIL) seeks invariant relations between graphs and labels under distribution shifts. Recent works try to extract an invariant subgraph to improve out-of-di…