Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives

TL;DR

Khan-GCL introduces a Kolmogorov-Arnold Network-based graph contrastive learning framework that enhances representation capacity and generates semantically meaningful hard negatives, leading to improved graph learning performance.

Contribution

It integrates KAN into GCL encoders and develops techniques for generating effective hard negatives based on KAN coefficients, advancing graph contrastive learning.

Findings

Achieves state-of-the-art results on multiple datasets.

Enhances discriminative power of graph representations.

Effectively generates semantically meaningful hard negatives.

Abstract

Graph contrastive learning (GCL) has demonstrated great promise for learning generalizable graph representations from unlabeled data. However, conventional GCL approaches face two critical limitations: (1) the restricted expressive capacity of multilayer perceptron (MLP) based encoders, and (2) suboptimal negative samples that either from random augmentations-failing to provide effective 'hard negatives'-or generated hard negatives without addressing the semantic distinctions crucial for discriminating graph data. To this end, we propose Khan-GCL, a novel framework that integrates the Kolmogorov-Arnold Network (KAN) into the GCL encoder architecture, substantially enhancing its representational capacity. Furthermore, we exploit the rich information embedded within KAN coefficient parameters to develop two novel critical feature identification techniques that enable the generation of semantically meaningful hard negative samples for each graph representation. These strategically constructed hard negatives guide the encoder to learn more discriminative features by emphasizing critical semantic differences between graphs. Extensive experiments demonstrate that our approach achieves state-of-the-art performance compared to existing GCL methods across a variety of datasets and tasks.