Can I read ID-MixGCL: Identity Mixup for Graph Contrastive Learning on EtoBox?

ID-MixGCL: Identity Mixup for Graph Contrastive Learning by Zhang, Gehang; Yu, Bowen; Cao, Jiangxia; Zhang, Xinghua; Sheng, Jiawei; Zhou, Chuan; Liu, Tingwen is a scholarly article available to read on EtoBox.

What is ID-MixGCL: Identity Mixup for Graph Contrastive Learning about?

Graph contrastive learning (GCL) has recently achieved substantial advancements. Existing GCL approaches compare two different ``views'' of the same graph in order to learn node/graph representations. The underlying assumption of these studies is that the graph augmentation strategy is capable of generating several different graph views such that the graph views are structurally different but semantically similar to the original graphs, and thus the ground-truth labels of the original and augmented graph/nodes can be regarded identical in contrastive learning. However, we observe that this assumption does not always hold. For instance, the deletion of a super-node within a social network can exert a substantial influence on the partitioning of communities for other nodes. Similarly, any perturbation to nodes or edges in a molecular graph will change the labels of the graph. Therefore, we believe that augmenting the graph, accompanied by an adaptation of the labels used for the contrastive loss, will facilitate the encoder to learn a better representation. Based on this idea, we propose ID-MixGCL, which allows the simultaneous interpolation of input nodes and corresponding identity

Author

Zhang, Gehang; Yu, Bowen; Cao, Jiangxia; Zhang, Xinghua; Sheng, Jiawei; Zhou, Chuan; Liu, Tingwen

Published

2023

Language

EN