Graph Contrastive and Supervised Anomaly Detection Scaling on Heterophilic Graphs

Abstract

Abstract: This report synthesises findings from 13 peer-reviewed papers addressing the following research question: How do graph contrastive anomaly detection models scale with graph size compared to supervised methods when evaluated on heterophilic graphs using the F1 score as the primary metric. With a long history of traditional Graph Anomaly Detection (GAD) algorithms and recently popular Graph Neural Networks (GNNs), it is still not clear (1) how they perform under a standard comprehensive setting, (2) whether GNNs can outperform traditional algorithms such as tree. 6 claims were extracted from source literature; 5 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 7.9/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How do graph contrastive anomaly detection models scale with graph size compared to supervised methods when evaluated on heterophilic graphs using the F1 score as the primary metric?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance