mlsanityData to 14 Oct 2026

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

arXiv 2505.15103 ↗First posted 21 May 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 21 May 2025.

Builds on

39 of 61 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  9. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  10. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  11. 2018Deep Graph Infomaxcited by 1,106
  12. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
27 more
  1. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  2. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  3. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  4. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  5. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  6. 2020Deep Graph Contrastive Representation Learningcited by 539
  7. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  8. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  9. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  10. 2020Hard Negative Mixing for Contrastive Learningcited by 402
  11. 2021Graph Contrastive Learning Automatedcited by 287
  12. 2021Pre-training Molecular Graph Representation with 3D Geometrycited by 248
  13. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  14. 2020AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversariescited by 90
  15. 2021ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learningcited by 72
  16. 2022Let Invariant Rationale Discovery Inspire Graph Contrastive Learningcited by 57
  17. 2024Enhancing Graph Collaborative Filtering with FourierKAN Feature Transformationcited by 42
  18. 2020Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Predictioncited by 41
  19. 2021Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Studycited by 36
  20. 2024GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networkscited by 32
  21. 2023The Expressive Power of Graph Neural Networks: A Surveycited by 27
  22. 2024TopoGCL: Topological Graph Contrastive Learningcited by 14
  23. 2023Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspectivecited by 13
  24. 2023Contrastive Learning with Consistent Representationscited by 6
  25. 2021Evaluating Modules in Graph Contrastive Learningcited by 4
  26. 2024GNN-SKAN: Harnessing the Power of SwallowKAN to Advance Molecular Representation Learning with GNNscited by 3
  27. 2024On Learning Discriminative Features from Synthesized Data for Self-Supervised Fine-Grained Visual Recognitioncited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Sizecited by 0