Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement

• URL: http://arxiv.org/abs/2606.20283v1
• Date: Thu, 18 Jun 2026 14:28:10 GMT
• Title: Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement
• Abstract summary: Boundary Embedding Shaping (BES) is an adaptive contrastive learning GNN plug-in module that selectively suppresses spurious structural noise at decision boundaries.<n>We show that 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.
• Score: 26.392300778291908
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• HOPE: Heterophily-Aware Open-Set Node Classification with Pseudo-Extrapolation [28.537709980685275]
  We propose HOPE, a Heterophily-aware Open-set node classification method with Pseudo-Extrapolation.<n> HOPE consistently outperforms state-of-the-art models, validating its effectiveness, robustness, and efficiency.
  arXiv  Detail & Related papers  (2026-09-08T12:53:52Z)
• NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption [67.57304101271096]
  Element-wise Masking (EM) suppresses edge-induced messages toward zero.<n>Noise Corruption (NC) perturbs each message through matched-norm random-direction corruption.<n>NICE, a Noise Corruption-based explanation framework, learns a Restoration Boundary (SRB) under NC-induced uncertainty.
  arXiv  Detail & Related papers  (2026-08-17T03:08:14Z)
• GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks [5.871974743871104]
  Graph Neural Networks (GNNs) are vulnerable to adversarial attacks, which inherently invert connectivity patterns by introducing disassortative edges.<n>We propose Graph Joint Disentanglement Network (GJDNet), a unified framework for robust node classification across diverse graph assortativity regimes.
  arXiv  Detail & Related papers  (2026-06-01T02:05:40Z)
• Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs [0.8188197619481464]
  Graph neural networks (GNNs) have achieved strong performance across various real-world domains.<n>They suffer from oversquashing, where long-range information is distorted as it is compressed through limited message-passing pathways.<n>We propose a novel graph learning framework that enriches node embeddings via cross-attentive cohesive subgraph representations.
  arXiv  Detail & Related papers  (2026-03-29T05:43:29Z)
• Limits of message passing for node classification: How class-bottlenecks restrict signal-to-noise ratio [0.6117371161379209]
  Message passing neural networks (MPNNs) are powerful models for node classification but suffer from performance limitations under heterophily and structural bottlenecks in the graph.<n>We provide a unifying statistical framework exposing the relationship between heterophily and bottlenecks through the signal-to-noise ratio (SNR) of MPNN representations.<n>We prove that optimal graph structures for maximising higher-order homophily are disjoint unions of single-class and two-class-bipartite clusters.<n>This yields BRIDGE, a graph ensemble-based rewiring algorithm that achieves near-perfect classification accuracy across all homophily
  arXiv  Detail & Related papers  (2025-08-25T09:25:14Z)
• ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions [64.17845687013434]
  We propose ReDiSC, a structured diffusion model for structured node classification.<n>We show that ReDiSC achieves superior or highly competitive performance compared to state-of-the-art GNN, label propagation, and diffusion-based baselines.<n> Notably, ReDiSC scales effectively to large-scale datasets on which previous structured diffusion methods fail due to computational constraints.
  arXiv  Detail & Related papers  (2025-07-19T04:46:53Z)
• Robust Learning on Noisy Graphs via Latent Space Constraints with External Knowledge [0.9320657506524149]
  We propose Latent Space Constrained Graph Neural Networks (LSC-GNN) to incorporate external "clean" links and guide embeddings of a noisy target graph.<n> Experiments on benchmark datasets show LSC-GNN outperforms standard and noise-resilient GNNs in graphs subjected to moderate noise.<n>Our results highlight LSC-GNN's potential to boost predictive performance and interpretability in settings with noisy relational structures.
  arXiv  Detail & Related papers  (2025-07-07T23:43:24Z)
• Residual Reweighted Conformal Prediction for Graph Neural Networks [14.329186221388087]
  Graph Neural Networks (GNNs) excel at modeling data but face significant challenges in high-stakes domains due to unquantified uncertainty.<n>We propose Residual Reweighted GNN (RR-GNN), a framework designed to generate minimal prediction sets with provable marginal coverage guarantees.<n>RR-GNN achieves improved efficiency over state-of-the-art methods, with no loss of coverage.
  arXiv  Detail & Related papers  (2025-06-09T15:19:17Z)
• A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs [54.62268052283014]
  We present a unified theoretical perspective based on the framework of signed graphs.<n>We show that many existing strategies implicitly introduce negative edges that alter message-passing to resist oversmoothing.<n>We propose Structural Balanced Propagation (SBP), a plug-and-play method that assigns signed edges based on either labels or feature similarity.
  arXiv  Detail & Related papers  (2025-02-17T03:25:36Z)
• Point Cloud Denoising With Fine-Granularity Dynamic Graph Convolutional Networks [58.050130177241186]
  Noise perturbations often corrupt 3-D point clouds, hindering downstream tasks such as surface reconstruction, rendering, and further processing. This paper introduces finegranularity dynamic graph convolutional networks called GDGCN, a novel approach to denoising in 3-D point clouds.
  arXiv  Detail & Related papers  (2024-11-21T14:19:32Z)
• Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module [65.81781176362848]
  Graph Neural Networks (GNNs) can learn from graph-structured data through neighborhood information aggregation. As the number of layers increases, node representations become indistinguishable, which is known as over-smoothing. We propose a textbfPosterior-Sampling-based, Node-distinguish Residual module (PSNR).
  arXiv  Detail & Related papers  (2023-05-09T12:03:42Z)
• Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily [58.76759997223951]
  We propose a new metric based on von Neumann entropy to re-examine the heterophily problem of GNNs. We also propose a Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets.
  arXiv  Detail & Related papers  (2022-03-19T14:26:43Z)
• Cyclic Label Propagation for Graph Semi-supervised Learning [52.102251202186025]
  We introduce a novel framework for graph semi-supervised learning called CycProp. CycProp integrates GNNs into the process of label propagation in a cyclic and mutually reinforcing manner. In particular, our proposed CycProp updates the node embeddings learned by GNN module with the augmented information by label propagation.
  arXiv  Detail & Related papers  (2020-11-24T02:55:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.