华东理工大学学报（自然科学版）2026，Vol.52Issue(1)：129-141,13.DOI:10.14135/j.cnki.1006-3080.20250429001
基于异构感知和对比学习的图推理机制
Research on Graph Reasoning Mechanism Based on Heterogeneous Perception and Contrastive Learning
摘要
Abstract
Heterogeneous graphs are instrumental in mining complex correlations within graph data,which holds significant importance in real-world applications.Traditional Graph Neural Networks(GNNs),however,are often confined to predefined tasks and rely on clearly labeled data along with fixed training mechanisms.This inherent limitation reduces their flexibility when dealing with open-world tasks.Moreover,existing research on integrating GNNs with Large Language Models(LLMs)predominantly focuses on homogeneous text-attributed graphs,failing to account for node heterogeneity.To address the challenges of misaligned heterogeneous feature representation spaces and open-domain task generalization,we propose a multi-hop graph reasoning mechanism that combines heterogeneous graph learning with contrastive learning.Specifically,the model decouples and reconstructs heterogeneous subgraphs based on meta-path symmetry.It achieves efficient fusion of topological embeddings and semantic representations through a differentiated attention mechanism and a hierarchical feature aggregation algorithm.To tackle modal misalignment,a progressive phase optimization strategy is adopted to train the graph query transformer,while a contrastive learning method is employed to bridge modal differences.Fine-grained feature associations are established via self-supervised image-text matching,and language modeling objectives are incorporated to enable the model to generate accurate answers to queries.Experimental results demonstrate that the proposed model exhibits strong adaptability to both predefined tasks and open-scene generalization.It also shows high-quality reasoning capabilities when addressing unseen questions in heterogeneous network question-answering tasks.关键词
异构图/复杂网络/对比学习/模态差异/特征关联Key words
heterogeneous graph/complex network/contrastive learning/modality discrepancy/feature association分类
信息技术与安全科学引用本文复制引用
黄如,吴新宇..基于异构感知和对比学习的图推理机制[J].华东理工大学学报（自然科学版）,2026,52(1):129-141,13.基金项目
国家自然科学基金(62322114) （62322114）
上海市自然科学基金(20ZR1413800) （20ZR1413800）
上海市重点实验室开放式基金(STCSM 22DZ2229005) （STCSM 22DZ2229005）
