β-GNN: A Robust Ensemble Approach Against Graph Structure Perturbation

Haci Ismail Aslan, Philipp Wiesner, Ping Xiong, Odej Kao
3/26/2025
cs.LGcs.AI

No official code found. Best implementation: AslantheAslan/beta-GNN (1 star, last commit 2025-03-06).

Abstract

Graph Neural Networks (GNNs) are playing an increasingly important role in the efficient operation and security of computing systems, with applications in workload scheduling, anomaly detection, and resource management. However, their vulnerability to network perturbations poses a significant challenge. We propose $β$-GNN, a model enhancing GNN robustness without sacrificing clean data performance. $β$-GNN uses a weighted ensemble, combining any GNN with a multi-layer perceptron. A learned dynamic weight, $β$, modulates the GNN's contribution. This $β$ not only weights GNN influence but also indicates data perturbation levels, enabling proactive mitigation. Experimental results on diverse datasets show $β$-GNN's superior adversarial accuracy and attack severity quantification. Crucially, $β$-GNN avoids perturbation assumptions, preserving clean data structure and performance.

View on arXivView PDF

Code Implementations(1)

AslantheAslan/beta-GNNCommunity100%

Implements the approach in paper "β-GNN: A Robust Ensemble Approach Against Graph Structure Perturbation"

10Shell, PythonMar 6, 20251 years ago

Similar Papers

Unifying Adversarial Perturbation for Graph Neural Networks

87% match2025

A Simple and Yet Fairly Effective Defense for Graph Neural Networks

86% match1 repo42024

Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defenses

86% match2025

SFR-GNN: Simple and Fast Robust GNNs against Structural Attacks

85% match2024

GNN-Ensemble: Towards Random Decision Graph Neural Networks

85% match2023

Budgeted Adversarial Attack against Graph-Based Anomaly Detection in Sensor Networks

85% match2025

Cite this paper

@article{aslan2025gnn,
  title  = {β-GNN: A Robust Ensemble Approach Against Graph Structure Perturbation},
  author = {Haci Ismail Aslan and Philipp Wiesner and Ping Xiong and Odej Kao},
  year   = {2025},
  eprint = {2503.20630},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.20630v1}
}

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/2503.20630.svg)](https://codeofpaper.com/paper/2503.20630)

Discussion