A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions

C Gong, Y Cheng, J Yu, C Xu, C Shan, S Luo… - arXiv preprint arXiv …, 2024 - arxiv.org
Graphs are structured data that models complex relations between real-world entities.
Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar …

A Simple Data Augmentation for Graph Classification: A Perspective of Equivariance and Invariance

Y Sui, S Wang, J Sun, Z Liu, Q Cui, L Li, J Zhou… - ACM Transactions on …, 2024 - dl.acm.org
In graph classification, the out-of-distribution (OOD) issue is attracting great attention. To
address this issue, a prevailing idea is to learn stable features, on the assumption that they …

Self-attentive Rationalization for Interpretable Graph Contrastive Learning

S Li, Y Luo, A Zhang, X Wang, L Li, J Zhou… - ACM Transactions on … - dl.acm.org
Graph augmentation is the key component to reveal instance-discriminative features of a
graph as its rationale–an interpretation for it–in graph contrastive learning (GCL). And …