When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty
This addresses the challenge of handling unlabeled data in graph learning for applications like social networks or knowledge graphs, but it appears incremental as it builds on existing LLM-based methods for text-attributed graphs.
The paper tackles the problem of data uncertainty in open-world graph learning, particularly with limited labeling and unknown-class nodes, by proposing the Open-world Graph Assistant (OGA) framework, which integrates semantics and topology for unknown-class rejection and enables model updates using newly annotated nodes, demonstrating effectiveness in experiments.
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.