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

2025/05/21 by Zihu Wang, Wang, Zihu, Boxun Xu +5 · 1 citation
Computer Science · Neuroscience · #Advanced Graph Neural Networks #Brain Tumor Detection and Classification #FOS: Computer and information sciences #Machine Learning (cs.LG) #Text and Document Classification Technologies

paper · pdf · doi:10.48550/arxiv.2505.15103

openalex publication_date 2025/05/21 · openalex created_date 2025/10/15 · openalex updated_date 2026/07/28

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.

Citations

• GNN-SKAN: Harnessing the Power of SwallowKAN to Advance Molecular Representation Learning with GNNs
• On Learning Discriminative Features from Synthesized Data for Self-Supervised Fine-Grained Visual Recognition
• GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks
• Enhancing Graph Collaborative Filtering with FourierKAN Feature Transformation
• KAN: Kolmogorov-Arnold Networks
• TopoGCL: Topological Graph Contrastive Learning
• Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective
• Contrastive Learning with Consistent Representations
• Let Invariant Rationale Discovery Inspire Graph Contrastive Learning
• Pre-training Molecular Graph Representation with 3D Geometry
• ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
• Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study
• Evaluating Modules in Graph Contrastive Learning
• Graph Contrastive Learning Automated
• Adversarial Graph Augmentation to Improve Graph Contrastive Learning
• SimCSE: Simple Contrastive Learning of Sentence Embeddings
• SimCSE: Simple Contrastive Learning of Sentence Embeddings
• Learning Transferable Visual Models From Natural Language Supervision
• Graph Contrastive Learning with Augmentations
• Hard Negative Mixing for Contrastive Learning
• TUDataset: A collection of benchmark datasets for learning with graphs
• Deep Graph Contrastive Representation Learning
• A Simple Framework for Contrastive Learning of Visual Representations
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Momentum Contrast for Unsupervised Visual Representation Learning
• Momentum Contrast for Unsupervised Visual Representation Learning
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Strategies for Pre-training Graph Neural Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Deep Graph Infomax
• Representation Learning with Contrastive Predictive Coding
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• MoleculeNet: A Benchmark for Molecular Machine Learning
• Geometric deep learning on graphs and manifolds using mixture model CNNs
• Adam: A Method for Stochastic Optimization
• Multilayer feedforward networks are universal approximators
• Some Mathematical Notes on Three-Mode Factor Analysis
• Gradient-based learning applied to document recognition

Cited by

• Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size

Related

• ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning
• Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling
• An Empirical Study of Graph Contrastive Learning
• Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning
• HyperGCL: Multi-Modal Graph Contrastive Learning via Learnable Hypergraph Views