← Search

Vincent Lee

2 accepted papers

2023

Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs

ICML 2023poster

Real-world graphs generally have only one kind of tendency in their connections. These connections are either homophilic-prone or heterophily-prone. While graphs with homophily-prone edges tend to connect nodes with the same class (i.e., intra-class nodes), heterophily-prone edges tend to build rela…

2022

Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination

NeurIPS 2022accept

Graph contrastive learning (GCL) alleviates the heavy reliance on label information for graph representation learning (GRL) via self-supervised learning schemes. The core idea is to learn by maximising mutual information for similar instances, which requires similarity computation between two node i…