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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Zihu, Xu, Boxun, Geng, Hejia, Li, Peng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912526605746176
author Wang, Zihu
Xu, Boxun
Geng, Hejia
Li, Peng
author_facet Wang, Zihu
Xu, Boxun
Geng, Hejia
Li, Peng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15103
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives
Wang, Zihu
Xu, Boxun
Geng, Hejia
Li, Peng
Machine Learning
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.
title Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives
topic Machine Learning
url https://arxiv.org/abs/2505.15103