Semi-Supervised Multi-View Graph Anomaly Detection with Limited Labeled Data

This report synthesises findings from 12 peer-reviewed papers addressing the following research question: How does the sample efficiency of semi-supervised multi-view graph anomaly detection frameworks compare to single-view methods when trained with less than 5\% labeled anomalous nodes. 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 8.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the sample efficiency of semi-supervised multi-view graph anomaly detection frameworks compare to single-view methods when trained with less than 5% labeled anomalous nodes?

Autonomous literature synthesis. Automated review score: 8.3/10. Full text and citation available at Assignee Research.