文献类型：期刊文献

中文题名：基于异构感知和对比学习的图推理机制

英文题名：Research on Graph Reasoning Mechanism Based on Heterogeneous Perception and Contrastive Learning

作者：黄如[1];吴新宇[1]

机构：[1]华东理工大学信息科学与工程学院,上海200237

年份：2026

卷号：52

期号：1

起止页码：129

中文期刊名：华东理工大学学报(自然科学版)

外文期刊名：Journal of East China University of Science and Technology

收录：;北大核心:【北大核心2023】；

基金：国家自然科学基金(62322114);上海市自然科学基金(20ZR1413800);上海市重点实验室开放式基金(STCSM 22DZ2229005)。

语种：中文

中文关键词：异构图;复杂网络;对比学习;模态差异;特征关联

外文关键词：heterogeneous graph;complex network;contrastive learning;modality discrepancy;feature association

摘要：传统图神经网络(GNN)通常局限于预设任务,依赖明确的标记数据和固定的训练机制,导致其在处理开放式任务时灵活性不足;现有图神经网络和大型语言模型的交叉领域(GNN-LLM)的研究多聚焦于同质化的文本属性图,未考虑到节点异质性问题。针对异构特征表征空间错位和开放域任务泛化的问题,本文提出了一个异构感知图学习联合对比学习的多跳图形推理机制:该模型基于元路径对称性解耦并重构异构子图,通过差异化注意力机制和层次化特征聚合算法,实现拓扑嵌入与语义表示的高效融合;针对模态对齐难题,采用渐进式阶段优化策略训练图形查询转换器;基于对比学习方法弥合模态差异,通过自监督的图文匹配建立细粒度特征关联,融合语言建模目标促使模型生成问题的有效回答。实验结果表明,该模型兼具预定义任务适配性与开放场景泛化性,在异构网络问答任务中展现出对未见问题的高质量推理能力。
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.