A new benchmark for graph anomaly detection on million-scale graphs with rare anomalies and missing data shows that most models fail to scale or detect anomalies effectively under realistic conditions.
Proceedings of the Learning on Graphs Conference , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
GAD in the Wild: Benchmarking Graph Anomaly Detection under Realistic Deployment Challenges
A new benchmark for graph anomaly detection on million-scale graphs with rare anomalies and missing data shows that most models fail to scale or detect anomalies effectively under realistic conditions.