用大模型解决开放世界图数据中未知类节点的不确定性问题
When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty
- 结合语义与拓扑信息动态识别未知类节点
- 支持新标注节点更新模型，提升开放场景适应性
- 适合处理标签稀缺、类别未知的现实图数据
大语言模型（LLMs）在文本属性图（TAG）学习中取得显著进展，但现有方法在开放世界场景下对数据不确定性的处理仍不足，尤其体现在标签有限和未知类别节点方面。以往方案通常依赖孤立的语义或结构方法进行未知类排斥，缺乏有效的标注流程。为此，我们提出开放世界图助手（OGA），一个基于LLM的框架，包含自适应标签可追溯性机制，融合语义与拓扑信息实现未知类排斥，并配备图标签标注器，支持利用新标注节点更新模型。大量实验表明，OGA在有效性与实用性上均表现优异。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。