2 papers
cs.LG2026
Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors
Iyad Assaad Nekka, Hamida Seba, Walid Khaled Hidouci +1
Anomaly detection in dynamic graphs underpins financial fraud analysis, intrusion detection, and platform integrity, where automated decisions require human-interpretable justifica…
cs.LG2026
Dual Spatial-Temporal Attribution: Architecture-Aligned Post-Hoc Explainability for Recurrent Graph Anomaly Detection
Iyad Assaad Nekka, Hamida Seba, Khaled Walid Hidouci +1
Deep learning detectors for anomalies in dynamic graphs have reached strong accuracy, yet they remain opaque: when an edge is flagged, the analyst receives a score but no reason. T…