.png){kind=icon}
.png){kind=icon}
Return
Hyperedge Graph Contrastive Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2024.3435861.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Although various graph contrastive learning (GCL) techniques have been employed to generate augmented views and maximize their mutual information, current solutions only consider the pairwise relationships based on edges, neglecting the high-order information that can help generate more informative augmented views and make better contrast. To fill in this gap, we propose to leverage hyperedge to facilitate GCL, as it connects two or more nodes and can model high-order relationships among multiple nodes. More specifically, hyperedges are constructed based on the original graph. Then, we conduct node-level PageRank based on hyperedges and hyperedge-level PageRank based on nodes to generate augmented views. As to the contrasting stage, different from existing GCL methods that simply treat the corresponding nodes of the anchor in different views as positives and overlook certain nodes strongly associated with the anchor, we build the positives and negatives based on hyperedges, where whether a node is a positive is determined by the number of hyperedges it coexists with the anchor. We compare our hyperedge GCL with state-of-the-art methods on downstream tasks, and the empirical results validate the superiority of our proposal. Further experiments on graph augmentation and graph contrastive loss also demonstrate the effectiveness of the proposed modules.
Keywords:
Graph augmentation
graph contrastive learning
graph representation learning
graph representation learning
graph self-supervised learning
graph self-supervised learning
hyperedge
hyperedge
graph self-supervised learning
hyperedge
Journal
IF:
10.4
Papers:
6.8K
Citations:
3.2W