arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.14846cs.LG
收藏

基于张量积图卷积表示的图边表示方法

Graph Edge Representation via Tensor Product Graph Convolutional Representation

School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院);Key Laboratory of Multimodal Cognitive Computation(多模态认知计算重点实验室)

Bo Jiang, Sheng Ge, Ziyan Zhang, Beibei Wang, Jin Tang, Bin Luo

AI总结:

针对现有图卷积无法处理带高维边特征图的问题,本文结合张量收缩表示与张量积图扩散理论提出TPGC算子以获取边嵌入,补充传统图卷积并在多任务中验证有效。

摘要:

图卷积网络(GCNs)已得到广泛研究,其核心是图上卷积算子的定义。但现有图卷积(GC)算子主要基于邻接矩阵和节点特征定义,通常聚焦于获取有效的节点嵌入,无法用于处理带有(高维)边特征的图。为解决该问题,本文利用张量收缩表示与张量积图扩散理论,在带边特征的图上类比定义了一种有效卷积算子,命名为Tensor Product Graph Convolution(TPGC,张量积图卷积)。所提出的TPGC旨在获取有效的边嵌入,为传统图卷积(GCs)提供了互补模型,可处理更通用的同时含节点与边特征的图数据分析任务。多项图学习任务的实验结果证明了所提TPGC的有效性。

英文摘要:

Graph Convolutional Networks (GCNs) have been widely studied. The core of GCNs is the definition of convolution operators on graphs. However, existing Graph Convolution (GC) operators are mainly defined on adjacency matrix and node features and generally focus on obtaining effective node embeddings which cannot be utilized to address the graphs with (high-dimensional) edge features. To address this problem, by leveraging tensor contraction representation and tensor product graph diffusion theories, this paper analogously defines an effective convolution operator on graphs with edge features which is named as Tensor Product Graph Convolution (TPGC). The proposed TPGC aims to obtain effective edge embeddings. It provides a complementary model to traditional graph convolutions (GCs) to address the more general graph data analysis with both node and edge features. Experimental results on several graph learning tasks demonstrate the effectiveness of the proposed TPGC.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑