Certifiably Robust Graph Contrastive Learning

Min Lin, Teng Xiao, Enyan Dai, Xiang Zhang, Suhang Wang
2/12/2026

No official code found. Best implementation: ventr1c/RES-GCL (11 stars, Apache-2.0, last commit 2024-01-22).

Abstract

Graph Contrastive Learning (GCL) has emerged as a popular unsupervised graph representation learning method. However, it has been shown that GCL is vulnerable to adversarial attacks on both the graph structure and node attributes. Although empirical approaches have been proposed to enhance the robustness of GCL, the certifiable robustness of GCL is still remain unexplored. In this paper, we develop the first certifiably robust framework in GCL. Specifically, we first propose a unified criteria to evaluate and certify the robustness of GCL. We then introduce a novel technique, RES (Randomized Edgedrop Smoothing), to ensure certifiable robustness for any GCL model, and this certified robustness can be provably preserved in downstream tasks. Furthermore, an effective training method is proposed for robust GCL. Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed method in providing effective certifiable robustness and enhancing the robustness of any GCL model. The source code of RES is available at https://github.com/ventr1c/RES-GCL.

View on arXivView PDF

Code Implementations(1)

ventr1c/RES-GCLCommunity63%
Apache-2.0

An official PyTorch implementation of "Certifiably Robust Graph Contrastive Learning" (NeurIPS 2023)

110Shell, PythonNov 16, 20222 years agoApache-2.0

Similar Papers

Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks

84% match2024

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks

83% match1 repo22026

On the Adversarial Robustness of Graph Contrastive Learning Methods

83% match2023

Robustness Verification of Graph Neural Networks Via Lightweight Satisfiability Testing

82% match2025

Improving Graph Neural Network Training, Defense and Hypergraph Partitioning via Adversarial Robustness Evaluation

82% match2024

Structure-Aware Robustness Certificates for Graph Classification

82% match2023

Cite this paper

@article{lin2026certifiably,
  title  = {Certifiably Robust Graph Contrastive Learning},
  author = {Min Lin and Teng Xiao and Enyan Dai and Xiang Zhang and Suhang Wang},
  year   = {2026},
  eprint = {2310.03312},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/pdf/2310.03312},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.03312.svg)](https://codeofpaper.com/paper/2310.03312)

Discussion