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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yujun, Zhang, Hongyuan, Yuan, Yuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910745932857344
author Li, Yujun
Zhang, Hongyuan
Yuan, Yuan
author_facet Li, Yujun
Zhang, Hongyuan
Yuan, Yuan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11075
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model
Li, Yujun
Zhang, Hongyuan
Yuan, Yuan
Machine Learning
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.
title Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model
topic Machine Learning
url https://arxiv.org/abs/2412.11075