Improving Augmentation Consistency for Graph Contrastive Learning

doi:10.1016/j.patcog.2023.110182

Improving Augmentation Consistency for Graph Contrastive Learning

2024-04-01

4

PRE

AI

DOI：10.1016/j.patcog.2023.110182

Original

Original request for help

Save

Abstract

En 中文

Graph contrastive learning (GCL) enhances unsupervised graph representation by generating different con-trastive views, in which properties of augmented nodes are required to be aligned with their anchors. However, we find that in some existing GCL methods, it is hard to inherit semantic and structural properties of graphs from anchor views due to inconsistent augmentation schemes, which may hurt node consistency in augmented views. In this paper, we present ConGCL to improve node consistency and enhance node classification. Specifically, we first consider context entailment, which integrates the semantic and structural properties to better mine the underlying consistency relationships of nodes. Beneficial from this, we then design a novel consistency improvement loss to maintain augmentation consistency agreement among positive node pairs under stochastic augmentation schemes. To investigate the effectiveness of ConGCL on improving augmentation consistency and enhancing node classification, we conduct empirical study and extensive experiments on benchmark datasets. The code is available at: https://github.com/brysonwx/ConGCL.

Keywords:

Graph contrastive learning

Augmentation consistency

Improving Augmentation Consistency for Graph Contrastive Learning

Abstract

Journal

Organization