Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model

TL;DR

This paper introduces AFECL, a novel augmentation-free graph contrastive learning model that efficiently learns edge features by embedding connected node pairs, achieving state-of-the-art results in link prediction and node classification.

Contribution

AFECL is the first augmentation-free GCL model that explicitly learns edge features through a novel embedding and contrastive scheme, reducing computational costs.

Findings

AFECL outperforms recent GCL methods and some supervised GNNs.

AFECL achieves state-of-the-art results on link prediction.

AFECL performs well with extremely scarce labels.

Abstract

Graph contrastive learning (GCL) aims to learn representations from unlabeled graph data in a self-supervised manner and has developed rapidly in recent years. However, edgelevel contrasts are not well explored by most existing GCL methods. Most studies in GCL only regard edges as auxiliary information while updating node features. One of the primary obstacles of edge-based GCL is the heavy computation burden. To tackle this issue, we propose a model that can efficiently learn edge features for GCL, namely AugmentationFree Edge Contrastive Learning (AFECL) to achieve edgeedge contrast. AFECL depends on no augmentation consisting of two parts. Firstly, we design a novel edge feature generation method, where edge features are computed by embedding concatenation of their connected nodes. Secondly, an edge contrastive learning scheme is developed, where edges connecting the same nodes are defined as positive pairs, and other edges are defined as negative pairs. Experimental results show that compared with recent state-of-the-art GCL methods or even some supervised GNNs, AFECL achieves SOTA performance on link prediction and semi-supervised node classification of extremely scarce labels. The source code is available at https://github.com/YujunLi361/AFECL.