计算机科学与探索2026，Vol.20Issue(8)：2241-2250,10.DOI:10.3778/j.issn.1673-9418.2510056
基于高效思维链微调的图表示学习方法
Efficient Chain-of-Thought Guided Instruction Tuning for Graph Representation Learning
摘要
Abstract
Large language models(LLMs)have demonstrated remarkable capabilities in natural language understanding and multi-step reasoning.Transferring these reasoning advantages to graph-structured tasks has become a crucial direction in graph learning.However,directly applying LLMs to graph data faces challenges such as significant modal disparity and the difficulty of effectively encoding structural information.To address the limitations of existing methods,including insufficient graph-text alignment,the absence of explicit reasoning processes,and high fine-tuning costs,this paper proposes GraphCoT,a graph representation learning approach based on efficient chain-of-thought(CoT)fine-tuning.The core of this approach lies in a high-quality CoT distillation mechanism,where a powerful teacher model is used to generate instruction data containing intermediate reasoning paths,thereby explicitly guiding the student model to learn multi-step reasoning with minimal training data.Additionally,GraphCoT introduces a graph-text alignment module to achieve cross-modal alignment between graph representations and language space,and adopts a lightweight two-stage training strategy that prioritizes modal alignment before task-specific fine-tuning.This approach significantly reduces training costs while balancing efficiency and transferability.Experimental results on node classification and link prediction tasks across multiple datasets demonstrate that GraphCoT outperforms existing state-of-the-art methods in accuracy and generalization,validating the effectiveness of both the CoT distillation mechanism and the proposed alignment strategy in graph representation learning.关键词
图表示学习/思维链/图编码器/跨模态Key words
graph representation learning/chain-of-thought/graph encoder/cross-modal分类
信息技术与安全科学引用本文复制引用
王艺铭,李倩,杜云涛,崔立真,闫中敏..基于高效思维链微调的图表示学习方法[J].计算机科学与探索,2026,20(8):2241-2250,10.基金项目
国家自然科学基金(62402293) （62402293）
山东省自然科学基金(ZR2025QC1570) （ZR2025QC1570）
山东大学基础研究基金. This work was supported by the National Natural Science Foundation of China(62402293),the Natural Science Foundation of Shandong Province(ZR2025QC1570),and the Fundamental Research Fund of Shandong University. （62402293）
