EUVIMEDEUVIMED entdecken
Crossref

Multi-dimensional Adaptive Mix-hop Contextual Learning Framework for Universal Graph Anomaly Detection

Zhaowei Liu, Leilei Jiang, Haitao Yang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15412-15420

DOI: 10.1609/aaai.v40i18.38568 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhaowei Liu und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph Anomaly Detection (GAD) focuses on identifying instances that deviate from normal patterns in graph-structured data. Although substantial progress has been made in this field, current approaches are constrained by the "one-dataset-one-model" paradigm, exhibiting limited generalization across heterogeneous graphs, poor adaptability in few-shot scenarios, and inefficient cross-domain deployment. To overcome these limitations, we propose SAARCS, a universal GAD framework capable of performing anomaly detection across diverse graph datasets without requiring any target data training. SAARCS aligns feature dimensions through composite spatial smoothness, learns graph embeddings via an adaptive-hop attention encoder, and predicts node abnormality using only a small set of normal context nodes. Extensive experiments on eight real-world datasets demonstrate that our approach achieves superior performance compared to state-of-the-art baselines.

Zitieren

APA

Liu, Z., Jiang, L., & Yang, H. (2026). Multi-dimensional Adaptive Mix-hop Contextual Learning Framework for Universal Graph Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15412-15420. https://doi.org/10.1609/aaai.v40i18.38568

Vancouver

Liu Z, Jiang L, Yang H. Multi-dimensional Adaptive Mix-hop Contextual Learning Framework for Universal Graph Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15412-15420. doi:10.1609/aaai.v40i18.38568

BibTeX
@article{Liu2026,
  author = {Liu, Zhaowei and Jiang, Leilei and Yang, Haitao},
  title = {Multi-dimensional Adaptive Mix-hop Contextual Learning Framework for Universal Graph Anomaly Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {18},
  pages = {15412--15420},
  doi = {10.1609/aaai.v40i18.38568}
}
Kostenlos starten →