ID-MixGCL: Identity Mixup for Graph Contrastive Learning

TL;DR

ID-MixGCL introduces a novel graph contrastive learning method that interpolates input nodes and labels to better handle structural changes, leading to improved graph and node classification performance.

Contribution

It proposes ID-MixGCL, a new approach that combines node and label interpolation for more effective graph contrastive learning under label-changing perturbations.

Findings

Significant performance improvements on multiple datasets.

Enhanced ability to learn fine-grained representations.

Outperforms state-of-the-art methods by 3-29%.

Abstract

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 labels to obtain soft-confidence samples, with a controllable degree of change, leading to the capture of fine-grained representations from self-supervised training on unlabeled graphs. Experimental results demonstrate that ID-MixGCL improves performance on graph classification and node classification tasks, as demonstrated by significant improvements on the Cora, IMDB-B, IMDB-M, and PROTEINS datasets compared to state-of-the-art techniques, by 3-29% absolute points.