发表机构
Chungbuk National University; Chungnam National University; The Pennsylvania State University（忠北国立大学; 忠南国立大学; 宾夕法尼亚州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对文本属性图小样本节点分类中现有方法LLM信息利用不均、成本高的问题，提出置信感知双教师学习框架CoTeach，动态为节点选更可靠教师，提升性能并降低LLM成本。
AI 中文摘要
文本属性图（TAGs）整合了图结构与节点关联的文本属性，近期研究越来越多地利用大语言模型（LLMs）提升小样本场景下的TAG学习效果。然而现有方法通常在所有节点上统一使用LLM衍生的信息，尽管其可靠性存在显著差异，还会产生可观的金钱成本。我们认为不同节点的最合适监督来源可能不同，因为图神经网络（GNNs）和LLMs在利用结构信息和语义信息上分别具有互补优势。为此，我们提出CoTeach，一个置信感知双教师学习框架，它为每个节点动态选择更可靠的教师。实验结果表明，CoTeach在持续提升小样本节点分类性能的同时，减少了不必要的LLM使用及相关金钱成本。
英文摘要
Text-Attributed Graphs (TAGs) integrate graph structures and node-associated textual attributes, and recent studies have increasingly leveraged Large Language Models (LLMs) to improve TAG learning in few-shot settings. However, existing approaches typically utilize LLM-derived information uniformly across all nodes, despite substantial variations in its reliability, while also incurring considerable monetary costs. We argue that the most appropriate source of supervision may differ across nodes, as Graph Neural Networks (GNNs) and LLMs exhibit complementary strengths in exploiting structural and semantic information, respectively. To this end, we propose CoTeach, a Confidence-aware dual-teacher learning framework that dynamically selects the more reliable teacher for each node. Experimental results demonstrate that CoTeach consistently improves few-shot node classification performance while reducing unnecessary LLM utilization and associated monetary costs.
