aiqbench analysis
The proposed CoTeach framework optimizes few-shot node classification on text-attributed graphs by dynamically selecting between Graph Neural Networks and Large Language Models based on their respective confidence levels. This approach not only enhances classification accuracy but also significantly reduces the computational overhead and monetary costs associated with indiscriminate LLM usage. By leveraging the complementary strengths of structural and semantic information, the method offers a more efficient pathway for integrating foundation models into graph learning tasks.
Who Should Teach? Confidence-Aware Dual-Teacher Learning for Few-Shot Node Classification on Text-Attributed Graphs
arXiv:2608.22127v1 Announce Type: new Abstract: 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.
Title:Who Should Teach? Confidence-Aware Dual-Teacher Learning for Few-Shot Node Classification on Text-Attributed Graphs
Abstract: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.
Machine Learning (cs.LG); Social and Information Networks (cs.SI)
arXiv:2608.22127 [cs.LG]
(or arXiv:2608.22127v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.22127 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 233 words
Related coverage
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
I Did This Without Your Knowledge
LessWrong · Oct 17, 2026
Research Note: Filtering Subversion-Relevant Information From Pretraining Data Is Feasible
LessWrong · Oct 5, 2026
Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching
arXiv · Jun 12, 2026