AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

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

Zihu Wang, Boxun Xu, Hejia Geng, Peng Li

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Graph contrastive learning analysis · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace MLP encoder with KAN encoder in GraphCL (no hard negatives) (ablation)GraphCL · MUTAGaccuracy: 86.8 -> 88.4Improved
replace MLP encoder with KAN encoder in GraphCL (no hard negatives) (ablation)GraphCL · TU-datasets averageaverage accuracy: 75.7 -> 76.8Improved
replace MLP encoder with KAN encoder in JOAOv2 (ablation)JOAOv2 · MUTAGaccuracy: 87.7 -> 88.6Improved
add CKFI hard negatives on top of KAN encoder (ablation)Khan-GCL · TU-datasets averageaverage accuracy: 76.8 -> 78.6Improved
add Khan-GCL hard negatives to JOAOv2 with KAN (ablation)JOAOv2 · MUTAGaccuracy: 88.6 -> 92.1Improved
use random Gaussian perturbation on all dimensions instead of CKFI-guided perturbation (ablation)Khan-GCL · TU-datasets averageaverage accuracy: 76.8 -> 76.6No clear effect
add discriminative dimension perturbation to independent-only perturbation (ablation)Khan-GCL · TU-datasets averageaverage accuracy: 77.7 -> 78.6Improved
add independent dimension perturbation to discriminative-only perturbation (ablation)Khan-GCL · TU-datasets averageaverage accuracy: 77.8 -> 78.6Improved
use both CKFI feature types in perturbation (ablation)Khan-GCL · TU-datasetsaccuracyImproved
Khan-GCL vs CI-GCL on some individual datasetsKhan-GCL · BBBP, BACE transferROC-AUC: BBBP 73.5 vs 74.4; BACE 80.9 vs 84.4Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy