Paper Info
Title
Graph Neural Networks Beyond Compromise Between Attribute and Topology
Abstract
ABSTRACT Although existing Graph Neural Networks (GNNs) based on message passing achieve state-of-the-art, the over-smoothing issue, node similarity distortion issue and dissatisfactory link prediction performance can’t be ignored. This paper summarizes these issues as the interference between topology and attribute for the first time. By leveraging the recently proposed optimization perspective of GNNs, this interference is analyzed and ascribed to that the learned representation in GNNs essentially compromises between the topology and node attribute. To alleviate the interference, this paper attempts to break this compromise by proposing a novel objective function, which fits node attribute and topology with different representations and introduces mutual exclusion constraints to reduce the redundancy in both representations. The mutual exclusion employs the statistical dependence, which regards the representations from topology and attribute as the observations of two random variables, and is implemented with Hilbert-Schmidt Independence Criterion. Derived from the novel objective function, a novel GNN, i.e., Graph Neural Network Beyond Compromise (GNN-BC), is proposed to iteratively updates the representations of topology and attribute by simultaneously capturing semantic information and removing the common information, and the final representation is the concatenation of them. The performance improvements on node classification and link prediction demonstrate the superiority of GNN-BC on relieving the interference.
Year
DOI
Venue
2022
10.1145/3485447.3512069
International World Wide Web Conference
Keywords
DocType
Citations 
Graph neural networks, network topology, node attribute
Conference
0
PageRank 
References 
Authors
0.34
0
8
Name
Order
Citations
PageRank
Liang Yang121316.53
Wenmiao Zhou200.34
Weihang Peng300.68
Bingxin Niu402.03
Junhua Gu544.19
Chuan Wang601.69
Xiaochun Cao71986131.55
Dongxiao He820128.10