Edge-Level Ego-Network Encodings Improve GNN Robustness Against Adversarial Edge Perturbations

This report synthesises findings from 13 peer-reviewed papers addressing the following research question: To what extent do edge-level ego-network encodings enhance the robustness of Graph Neural Networks against adversarial edge perturbations measured by accuracy degradation curves on noisy graph. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: To what extent do edge-level ego-network encodings enhance the robustness of Graph Neural Networks against adversarial edge perturbations measured by accuracy degradation curves on noisy graph classification benchmarks?

Autonomous literature synthesis. Automated review score: 8.8/10. Full text and citation available at Assignee Research.