EUVIMEDEUVIMED entdecken
Crossref

Disentangled Generation-Based Prototypical Alignment for Few-Shot Unsupervised Domain Adaptation in Graph-Level Anomaly Detection

Zhibin Ni, Chenghao Zhang, Hai Wan, Xibin Zhao

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (29) · 24558-24566

DOI: 10.1609/aaai.v40i29.39639 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhibin Ni und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph-Level Anomaly Detection (GLAD) seeks to identify anomalous graphs within graph datasets, which has significant applications across diverse real-world fields. Most existing GLAD methods are trained in an unsupervised manner due to high costs for labeling, resulting in sub-optimal performance when compared to supervised methods. To fill this gap, we propose a Disentangled Generation-Based Prototypical Alignment (DGPA) method that extends graph-level anomaly detection to Few-Shot Unsupervised Domain Adaptation (FUDA) setting, aiming to identify anomalous graphs from a set of unlabeled graphs (target domain) by using partially labeled graphs from a different but related domain (source domain), which fulfills the practical requirement of transferring anomaly knowledge. This is specifically achieved through a dedicated Disentangled Sample Generation module, which addresses label scarcity by generating faithful samples with disentangled representation learning grounded in Information Bottleneck principle, along with a Graph-based Prototypical Self-Supervision module, which alleviates domain shift by encoding and aligning semantic structures in the shared latent space across domains in a self-supervised manner. Extensive experiments on five benchmark datasets reveal the effectiveness of our proposed DGPA.

Zitieren

APA

Ni, Z., Zhang, C., Wan, H., & Zhao, X. (2026). Disentangled Generation-Based Prototypical Alignment for Few-Shot Unsupervised Domain Adaptation in Graph-Level Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(29), 24558-24566. https://doi.org/10.1609/aaai.v40i29.39639

Vancouver

Ni Z, Zhang C, Wan H, Zhao X. Disentangled Generation-Based Prototypical Alignment for Few-Shot Unsupervised Domain Adaptation in Graph-Level Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(29):24558-24566. doi:10.1609/aaai.v40i29.39639

BibTeX
@article{Ni2026,
  author = {Ni, Zhibin and Zhang, Chenghao and Wan, Hai and Zhao, Xibin},
  title = {Disentangled Generation-Based Prototypical Alignment for Few-Shot Unsupervised Domain Adaptation in Graph-Level Anomaly Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {29},
  pages = {24558--24566},
  doi = {10.1609/aaai.v40i29.39639}
}
Kostenlos starten →