Recently, large language models (LLMs) have significantly advanced text-attributed graph (TAG) learning. However, existing methods inadequately handle data uncertainty in open-world scenarios, especially concerning limited labeling and unknown-class nodes. Prior solutions typically rely on isolated semantic or structural approaches for unknown-class rejection, lacking effective annotation pipelines. To address these limitations, we propose Open-world Graph Assistant (OGA), an LLM-based framework that combines adaptive label traceability, which integrates semantics and topology for unknown-class rejection, and a graph label annotator to enable model updates using newly annotated nodes. Comprehensive experiments demonstrate OGA's effectiveness and practicality.
@article{arxiv.2505.13989,
title = {When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty},
author = {Yanzhe Wen and Xunkai Li and Qi Zhang and Zhu Lei and Guang Zeng and Rong-Hua Li and Guoren Wang},
journal= {arXiv preprint arXiv:2505.13989},
year = {2025}
}