信息资源管理学报2025，Vol.15Issue(6)：129-142,14.DOI:10.13365/j.jirm.2025.06.129
基于异构图神经网络的知识重组预测框架研究
A Knowledge Recombination Prediction Framework Based on Heterogeneous Graph Neural Networks
摘要
Abstract
Knowledge recombination is pivotal for fostering innovation and interdisciplinary integration.Existing studies typically rely on homogenous knowledge networks for its early prediction,which fail to cap-ture the intricate relationships between knowledge units and their associated entities,thereby constraining predictive performance.To address this limitation,this paper proposes a knowledge-recombination predic-tion framework based on heterogeneous graph neural networks.The framework integrates multiple heteroge-neous entities and relations closely related to knowledge units,constructs an enriched heterogeneous knowl-edge network through diverse connection strategies,and employs a relation-aware graph convolutional net-work to predict potential recombination links.Empirical experiments in the cancer immunotherapy domain demonstrate that the proposed framework markedly outperforms traditional homogenous-network baselines,with the F1 score rising from 0.706 to 0.889.The results also confirm that connection strategies for hetero-geneous nodes significantly influence predictive performance,underscoring the importance of heterogenous network design in knowledge-recombination prediction.关键词
知识重组预测/异构图神经网络/链路预测/复杂网络/多元关系Key words
Knowledge recombination prediction/Heterogeneous graph neural network/Link prediction/Complex networks/Multiple relationship分类
社会科学引用本文复制引用
任安兴,杨冠灿,行佳鑫,张滋荷..基于异构图神经网络的知识重组预测框架研究[J].信息资源管理学报,2025,15(6):129-142,14.基金项目
本文系国家自然科学基金面上项目"复杂动态视角下的技术会聚形成机理及预测方法研究"(72274205)研究成果之一.(This paper is one of the outcomes of the General Program of the National Natural Science Foundation of China project"Research on the Formation Mechanism and Prediction Method of Technology Convergence from the Perspec-tive of Complex Dynamics"(72274205).) （72274205）
