EUVIMEDEUVIMED entdecken
Crossref

Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries

Yue Hou, Ruomei Liu, Yingke Su, Junran Wu, Ke Xu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (26) · 21797-21804

DOI: 10.1609/aaai.v40i26.39331 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yue Hou und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A key challenge in graph out-of-distribution (OOD) detection lies in the absence of ground-truth OOD samples during training. Existing methods are typically optimized to capture features within the in-distribution (ID) data and calculate OOD scores, which often limits pre-trained models from representing distributional boundaries, leading to unreliable OOD detection. Moreover, the latent structure of graph data is often governed by multiple underlying factors, which remains less explored. To address these challenges, we propose a novel test-time graph OOD detection method, termed BaCa, that calibrates OOD scores using dual dynamically updated dictionaries without requiring fine-tuning the pre-trained model. Specifically, BaCa estimates graphons and applies a mix-up strategy solely with test samples to generate diverse boundary-aware discriminative topologies, eliminating the need for exposing auxiliary datasets as outliers. We construct dual dynamic dictionaries via priority queues and attention mechanisms to adaptively capture latent ID and OOD representations, which are then utilized for boundary-aware OOD score calibration. To the best of our knowledge, extensive experiments on real-world datasets show that BaCa significantly outperforms existing state-of-the-art methods in OOD detection.

Zitieren

APA

Hou, Y., Liu, R., Su, Y., Wu, J., & Xu, K. (2026). Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries. Proceedings of the AAAI Conference on Artificial Intelligence, 40(26), 21797-21804. https://doi.org/10.1609/aaai.v40i26.39331

Vancouver

Hou Y, Liu R, Su Y, Wu J, Xu K. Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(26):21797-21804. doi:10.1609/aaai.v40i26.39331

BibTeX
@article{Hou2026,
  author = {Hou, Yue and Liu, Ruomei and Su, Yingke and Wu, Junran and Xu, Ke},
  title = {Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {26},
  pages = {21797--21804},
  doi = {10.1609/aaai.v40i26.39331}
}
Kostenlos starten →