Caihua Shan

How Powerful is Graph Convolution for Recommendation?

2021

Graph convolutional networks (GCNs) have recently enabled a popular class of algorithms for collaborative filtering (CF). Nevertheless, the theoretical underpinnings of their empirical successes remain elusive. In this paper, we endeavor to obtain a better …

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

2024 · arXiv (Cornell University)

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 features, have recently attracted significant attention and found many real-world …

Learning Prioritized Node-Wise Message Propagation in Graph Neural Networks (Extended Abstract)

2025

Graphs are ubiquitous in the real world, in graphs, nodes represent entities and edges capture their relationships. Recently, graph neural networks (GNNs) [3]–[6] have been proposed to integrate these two sources of information. In GNNs, …