mlsanityData to 14 Oct 2026

Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement

arXiv 2606.20283 ↗First posted 18 Jun 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) excel at aggregating neighbor information for classification, yet their performance is hindered by graph structural entanglement, where spurious correlations from semantically irrelevant neighbors contaminate node embeddings. This challenge is most acute for nodes near class boundaries in the embedding space, where amplified structural noise blurs decision boundaries and destabilizes predictions. Existing robust GNN methods largely treat all nodes uniformly, ignoring boundary vulnerabilities. In this paper, to improve classification performance, we tackle graph structural disentanglement by identifying boundary-region entanglement as the primary bottleneck and propose Boundary Embedding Shaping (BES), an adaptive contrastive learning GNN plug-in module that selectively suppresses spurious structural noise at decision boundaries with minimal model parameter perturbation. Extensive experiments demonstrate that BES consistently improves boundary discrimination and outperforms existing leading methods. Notably, BES boosts GCN performance by an average of 3.3% in node classification (up to 5.0% on WikiCS) and achieves superior accuracy in link prediction.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 63 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

40 of 63 references.

References · 40

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2020Supervised Contrastive Learningcited by 2,829
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  7. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  8. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  9. 2019Simplifying Graph Convolutional Networkscited by 1,477
  10. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  11. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  12. 2021How Attentive are Graph Attention Networks?cited by 835
28 more
  1. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  2. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  3. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  4. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
  5. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  6. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
  7. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
  8. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 260
  9. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 247
  10. 2021Contrastive Learning Inverts the Data Generating Processcited by 221
  11. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  12. 2020Disentangled Graph Collaborative Filteringcited by 118
  13. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 85
  14. 2023Multi-View Causal Representation Learning with Partial Observabilitycited by 74
  15. 2021ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learningcited by 72
  16. 2023Identifiability Results for Multimodal Contrastive Learningcited by 61
  17. 2022Identifying Weight-Variant Latent Causal Modelscited by 34
  18. 2023Identifiable Latent Polynomial Causal Models Through the Lens of Changecited by 23
  19. 2024Motif-aware Riemannian Graph Neural Network with Generative-Contrastive Learningcited by 23
  20. 2023Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similaritycited by 14
  21. 2025I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?cited by 13
  22. 2022Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptationcited by 12
  23. 2025Graph Neural Networks in Modern AI-aided Drug Discoverycited by 12
  24. 2023TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender Systemscited by 11
  25. 2024Beyond DAGs: A Latent Partial Causal Model for Multimodal Learningcited by 10
  26. 2025On the Value of Cross-Modal Misalignment in Multimodal Representation Learningcited by 10
  27. 2023Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Predictioncited by 8
  28. 2023Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of Onecited by 7

Built on by

Not cited yet.