Metraipolis › archive › dc_d8a7c0ae429e
Dual Spatial-Temporal Attribution: Architecture-Aligned Post-Hoc Explainability for Recurrent Graph Anomaly Detection — arXiv:2608.12441
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12441
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:17:58.688Z
- SHA-256 of the archived text
e9c312ea51741f4c2f0e8a311d9a885bd6fc9e44c0ac00d0fdc86a30b9a78e96- Stable URL of this page
https://metraipolis.com/documento/dc_d8a7c0ae429e
How to cite
Dual Spatial-Temporal Attribution: Architecture-Aligned Post-Hoc Explainability for Recurrent Graph Anomaly Detection — arXiv:2608.12441 — arXiv (en), https://arxiv.org/abs/2608.12441 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8a7c0ae429e (Metraipolis archive dc_d8a7c0ae429e, sha256 e9c312ea51741f4c2f0e8a311d9a885bd6fc9e44c0ac00d0fdc86a30b9a78e96)
BibTeX
@misc{dcd8a7c0ae429e,
title = {Dual Spatial-Temporal Attribution: Architecture-Aligned Post-Hoc Explainability for Recurrent Graph Anomaly Detection — arXiv:2608.12441},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12441},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8a7c0ae429e; sha256 e9c312ea51741f4c2f0e8a311d9a885bd6fc9e44c0ac00d0fdc86a30b9a78e96},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12441. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. This opacity is untenable in the cooperative, regulated information systems where such detectors are deployed, where automated decisions must be auditable and trustworthy. We address this gap for AddGraph, the foundational GCN+GRU framework for edge-level anomaly detection in dynamic graphs, which to our knowledge has never been equipped with any form of explainability. We present a strictly post-hoc explainability framework, X-AddGraph, built on a Dual Spatial-Temporal Attribution (DSTA) mechanism whose three components are each aligned with one of AddGraph's architectural modules: a gradient-based relevance attribution over the current adjacency structure (spatial), a direct reading of the contextual attention weights already computed during inference (short-term temporal, at zero additional cost), and a gradient rollback through the recurrent hidden states (long-term temporal). Because the detector is frozen, detection performance is preserved exactly (Delta AUC = 0, verified empirically to ten decimal places). On the UCI Message benchmark, our trained AddGraph baseline reaches an average per-snapshot AUC of 0.8705, exceeding the originally published result; X-AddGraph reproduces every score identically while adding explanations where none existed. Evaluated across four edge populations - confident true positives, low-confidence true positives, false positives, and random samples - the long-term attribution identifies historical snapshots carrying significantly more counterfactual signal than random selection (0.127 vs. 0.074), a capability that no spatially-blind explainer can provide. We release our implementation for full reproducibility. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.12441 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T04:13:06.673Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).