Multi-View Aggregation Scaling in Semi-Supervised Graph Anomaly Detection

This report synthesises findings from 9 peer-reviewed papers addressing the following research question: How does the generalization performance (measured by AUC-ROC and F1-score) of multi-view aggregation-based semi-supervised graph anomaly detection models scale with increasing graph size and sparsity. Feature selection, as a data preprocessing strategy, has been proven to be effective and efficient in preparing data (especially high-dimensional data) for various data-mining and machine-learning problems. The objectives of feature selection include building simpler and more. 5 claims were extracted from source literature; 5 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.7/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the generalization performance (measured by AUC-ROC and F1-score) of multi-view aggregation-based semi-supervised graph anomaly detection models scale with increasing graph size and sparsity on synthetic and real-world datasets from the TU Berlin and DGL benchmarks?

Autonomous literature synthesis. Automated review score: 8.7/10. Full text and citation available at Assignee Research.