摘要
近年来,图神经网络因能够高效处理异质图中的复杂结构和丰富语义信息而受到了广泛的关注。学习异质图的低维节点嵌入,同时为节点分类、节点聚类等下游任务保留异质结构和语义,是一个关键且具有挑战性的问题。现有研究主要基于元路径来设计模型,但这种方法至少存在两方面的局限性:1)合适元路径的选择通常需要专家知识或额外的标注信息;2)该方法限制了模型按预定义的模式学习,从而难以充分捕获网络的复杂性。针对这些问题,提出了一种多视图和语义感知的异质图注意力网络(Multi-view and Semantic-aware Heterogeneous Graph Attention Network,MS-HGANN)。该网络无需人工设计元路径,即可融合节点和关系中的丰富语义信息。MS-HGANN主要包括3个部分:特征映射、二阶特定视图自我图融合和语义感知。特征映射将特征映射到统一的节点特征空间;二阶特定视图自我图融合设计了特定关系的编码器和节点注意力学习节点在局部结构上的表示;语义感知设计了两种相互协调的注意力机制来评估节点和关系的重要性,从而得到最终的节点表示。在3个公开数据集上进行实验,结果表明,所提模型在节点分类和聚类任务上达到了先进水平。
In recent years,graph neural networks have received widespread attention for their ability to efficiently process complex structures and rich semantic information in heterogeneous graphs.Learning low-dimensional node embeddings of heterogeneous graphs while preserving the heterogeneous structure and semantics for downstream tasks such as node classification and node clustering is a critical and challenging problem.Existing studies mainly design models based on meta-paths,but this approach faces at least two limitations.1)The selection of suitable meta-paths usually requires expert knowledge or additional labelling information.2)The approach restricts the model from learning by predefined patterns,which makes it difficult to adequately capture the complexity of the network.To address these issues,a multi-view and semantic-aware heterogeneous graph attention network(MS-HGANN)is proposed to merge nodes and relationships without manually designing meta-paths with the MS-HGANN consists of three main components:feature mapping,second-order view-specific self-graph fusion,and semantic aware.Feature mapping maps features to a uniform node feature space.Second-order view-specific self-graph fusion designs relationship-specific encoders and node attention to learn node representations on local structures.Semantic aware designs two coordinated attention mechanisms to evaluate the importance of nodes and relationships to obtain the final node representations.Experimental results on three publicly available datasets show that the proposed model is state-of-the-art for node classification and clustering tasks.
作者
王静红
吴芝冰
王熙照
李昊康
WANG Jinghong;WU Zhibing;WANG Xizhao;LI Haokang(College of Computer and Cyber Security,Hebei Normal University,Shijiazhuang 050024,China;Hebei Provincial Key Laboratory of Network and Information Security,Shijiazhuang 050024,China;Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics&Data Security,Shijiazhuang 050024,China;Department of Computer Science and Software Engineering,Shenzhen University,Shenzhen,Guangdong 518060,China;Artificial Intelligence and Big Data College of Hebei University of Engineering and Technology,Shijiazhuang 050091,China)
出处
《计算机科学》
北大核心
2025年第6期167-178,共12页
Computer Science
基金
河北省自然科学基金(F2024205028,F2021205014)
河北省高等学校科学技术研究项(ZD2022139)。
关键词
图神经网络
异质图
图表示学习
异质图嵌入
异质网络
Graph neural networks
Heterogeneous graphs
Graph representation learning
Heterogeneous graph embedding
Heterogeneous networks
