Graph Reciprocal Neural Networks by Abstracting Node as Attribute

Liang Yang, Jiayi Wang, Dongxiao He, Chuan Wang, Xiaochun Cao, Bingxin Niu, Zhen Wang

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Graph neural network (GNN) can be formulated as the multiplication of the topology-related matrix (adjacency or Laplacian matrix) and node attribute matrix, i.e., operation in node-wise. Unfortunately, this unified formula reveals two inherent drawbacks. Firstly, the topology and node attribute are not reciprocal but biased. From employment, the topology information is repeatedly employed, while the node attribute is only used once. From parameterization perspective, the node attribute is parameterized with highly expressive MLPs, while topology is not. Secondly, the graph topology can not be fully explored. Only the local pairwise relation is explored, but the mesoscopic community structure, which is one of the most prominent characteristics of networks, is ignored. To alleviate these issues, this paper proposes the Graph Reciprocal Network (GRN) by treating node attribute and topology reciprocal. Firstly, it is illustrated that the node can be regarded and utilized as another kind of attribute. Secondly, a novel node representation scheme is proposed from the theory of Quadratic Networks, with a theoretical guarantee of the fine-grained element-wise product of the representations of the topology and attribute. Extensive experiments demonstrate the superior performance and robustness of the proposed GRN.

源语言英语
主期刊名Proceedings - 23rd IEEE International Conference on Data Mining, ICDM 2023
编辑Guihai Chen, Latifur Khan, Xiaofeng Gao, Meikang Qiu, Witold Pedrycz, Xindong Wu
出版商Institute of Electrical and Electronics Engineers Inc.
1463-1468
页数6
ISBN(电子版)9798350307887
DOI
出版状态已出版 - 2023
活动23rd IEEE International Conference on Data Mining, ICDM 2023 - Shanghai, 中国
期限: 1 12月 20234 12月 2023

出版系列

姓名Proceedings - IEEE International Conference on Data Mining, ICDM
ISSN(印刷版)1550-4786

会议

会议23rd IEEE International Conference on Data Mining, ICDM 2023
国家/地区中国
Shanghai
时期1/12/234/12/23

指纹

探究 'Graph Reciprocal Neural Networks by Abstracting Node as Attribute' 的科研主题。它们共同构成独一无二的指纹。

引用此