Hard Negative Mining vs. Random Sampling for GNN Robustness in Sparse Networks

This report synthesises findings from 10 peer-reviewed papers addressing the following research question: What is the comparative impact of hard negative mining versus random negative sampling on the robustness of graph neural networks for anomaly detection in highly sparse network regions. Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.0/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: What is the comparative impact of hard negative mining versus random negative sampling on the robustness of graph neural networks for anomaly detection in highly sparse network regions?

Autonomous literature synthesis. Automated review score: 8.0/10. Full text and citation available at Assignee Research.