EUVIMEDEUVIMED entdecken
Crossref

Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models

Xueqi Ma, Xingjun Ma, Sarah Monazam Erfani, Danilo Mandic, James Bailey

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (43) · 36714-36722

DOI: 10.1609/aaai.v40i43.40996 ↗

Kurz gefasst

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

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Developing open-set classification methods capable of classifying in-distribution (ID) data while detecting out-of-distribution (OOD) samples is essential for deploying graph neural networks (GNNs) in open-world scenarios. Existing methods typically treat all OOD samples as a single class, despite real-world applications—especially high-stake settings like fraud detection and medical diagnosis—demanding deeper insights into OOD samples, including their probable labels. This raises a critical question: Can OOD detection be extended to OOD classification without true label information? To answer this question, we introduce a Coarse-to-Fine open-set Classification (CFC) method that leverages large language models (LLMs) for text-attributed graphs. CFC consists of three key components: (1) A coarse classifier that utilizes LLM prompts for OOD detection and outlier label generation; (2) A GNN-based fine classifier trained with OOD samples from (1) for enhanced OOD detection and ID classification; and (3) Refined OOD classification achieved through LLM prompts and post-processed OOD labels. Unlike methods relying on synthetic or auxiliary OOD samples, CFC employs semantic OOD data-instances that are genuinely out-of-distribution based on their inherent meaning, thus improving interpretability and practical utility. CFC enhances OOD detection by 10% compared to state-of-the-art approaches on text-attributed graphs and in the text domain, while achieving up to 70% accuracy in OOD classification on graph datasets.

Zitieren

APA

Ma, X., Ma, X., Erfani, S. M., Mandic, D., & Bailey, J. (2026). Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(43), 36714-36722. https://doi.org/10.1609/aaai.v40i43.40996

Vancouver

Ma X, Ma X, Erfani SM, Mandic D, Bailey J. Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(43):36714-36722. doi:10.1609/aaai.v40i43.40996

BibTeX
@article{Ma2026,
  author = {Ma, Xueqi and Ma, Xingjun and Erfani, Sarah Monazam and Mandic, Danilo and Bailey, James},
  title = {Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {43},
  pages = {36714--36722},
  doi = {10.1609/aaai.v40i43.40996}
}
Kostenlos starten →