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 IEEE International Conference on Acoustics, Speech and Signal Processing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1roles
background 1polarities
background 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.