Graph Ranking Contrastive Learning: A Extremely Simple yet Efficient Method

TL;DR

GraphRank introduces a simple and efficient contrastive learning method for graphs that redefines negative samples to avoid false negatives, improving representation quality across multiple tasks.

Contribution

It proposes GraphRank, a novel contrastive learning approach that mitigates false negatives without increasing computational complexity.

Findings

Improves node, edge, and graph-level task performance

Reduces false negative impact in contrastive learning

Maintains efficiency with fewer negative samples

Abstract

Graph contrastive learning (GCL) has emerged as a representative graph self-supervised method, achieving significant success. The currently prevalent optimization objective for GCL is InfoNCE. Typically, it employs augmentation techniques to obtain two views, where a node in one view acts as the anchor, the corresponding node in the other view serves as the positive sample, and all other nodes are regarded as negative samples. The goal is to minimize the distance between the anchor node and positive samples and maximize the distance to negative samples. However, due to the lack of label information during training, InfoNCE inevitably treats samples from the same class as negative samples, leading to the issue of false negative samples. This can impair the learned node representations and subsequently hinder performance in downstream tasks. While numerous methods have been proposed to mitigate the impact of false negatives, they still face various challenges. For instance, while increasing the number of negative samples can dilute the impact of false negatives, it concurrently increases computational burden. Thus, we propose GraphRank, a simple yet efficient graph contrastive learning method that addresses the problem of false negative samples by redefining the concept of negative samples to a certain extent, thereby avoiding the issue of false negative samples. The effectiveness of GraphRank is empirically validated through experiments on the node, edge, and graph level tasks.