IEEE

Summary Graph Induced Invariant Learning for Generalizable Graph Learning

Abstract: As a promising strategy to achieve generalizable graph learning tasks, graph invariant learning emphasizes identifying invariant subgraphs for stable predictions on biased unknown ...
EurekAlert!

Invariant graph learning meets information bottleneck for out-of-distribution generalization

Graph out-of-distribution (OOD) generalization remains a major challenge in graph neural networks (GNNs). Invariant learning, aiming to extract invariant features across varied distributions, has ...
IEEE

GI-Graph: A Generative Invariant Graph Learning Scheme Towards Out-of-Distribution Generalization

Abstract: When distribution shifts occur between testing and training graph data, out-of-distribution (OOD) samples undermine the performance of graph neural networks (GNNs). To improve adaptive OOD ...
Armed robbery in Revesby

Invariant Graph Learning Tackles OOD Generalization

Graph out-of-distribution (OOD) generalization remains a major challenge in graph neural networks (GNNs). Invariant learning, aiming to extract invariant features across varied distributions, has ...
GitHub

Structural Invariance Matters: Rethinking Graph Rewiring through Graph Metrics

Graph rewiring techniques are used to modify the structure of graphs used to train models such as GNNs and graph transformers. However, rewiring inherently alters the structural properties of the ...