Homophily principle,\ie {} nodes with the same labels or similar attributes are more likely to
be connected, has been commonly believed to be the main reason for the superiority of …

Graph Contrastive Learning (GCL) has emerged as a highly effective self-supervised
approach in graph representation learning. However, prevailing GCL methods confront two …

Graph contrastive learning has made remarkable advances in settings where there is a
scarcity of task-specific labels. Despite these advances, the significant computational …

Graph augmentation has received great attention in recent years for graph contrastive
learning (GCL) to learn well-generalized node/graph representations. However, mainstream …

Graphs are ubiquitous for modeling complex relationships between objects across various
fields. Graph neural networks (GNNs) have become a mainstream technique for graph …

This paper introduces a novel generalized self-imitation learning ($\textbf {GSIL} $)
framework, which effectively and efficiently aligns large language models with offline …

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 …

Generating molecular structures with desired properties is a critical task with broad
applications in drug discovery and materials design. We propose 3M-Diffusion, a novel multi …

Abstract Graph Contrastive Learning (GCL) leverages graph structure and node feature
information to learn powerful node representations in a self-supervised manner, attracting …

Noncoding RNAs (ncRNAs), including long noncoding RNAs (lncRNAs) and microRNAs
(miRNAs), play crucial roles in gene expression regulation and are significant in disease …