Paper Info
Title
Learnable Structural Semantic Readout for Graph Classification
Abstract
With the great success of deep learning in various domains, graph neural networks (GNNs) also become a dominant approach to graph classification. By the help of a global readout operation that simply aggregates all node (or node-cluster) representations, existing GNN classifiers obtain a graph-level representation of an input graph and predict its class label using the representation. However, such global aggregation does not consider the structural information of each node, which results in information loss on the global structure. In this work, we propose structural semantic readout (SSRead) to summarize the node representations at the position-level, which allows to model the position-specific weight parameters for classification as well as to effectively capture the graph semantic relevant to the global structure. Given an input graph, SSRead aims to identify structurally-meaningful positions by using the semantic alignment between its nodes and structural prototypes, which encode the prototypical features of each position. The structural prototypes are optimized to minimize the alignment cost for all training graphs, while the other GNN parameters are trained to predict the class labels. Our experimental results demonstrate that SSRead significantly improves the classification performance and interpretability of GNN classifiers while being compatible with a variety of aggregation functions, GNN architectures, and learning frameworks.
Year
DOI
Venue
2021
10.1109/ICDM51629.2021.00142
2021 21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2021)
Keywords
DocType
ISSN
Graph classification, Graph neural networks, Global structural information, Learnable graph readout
Conference
1550-4786
Citations 
PageRank 
References 
0
0.34
0
Authors
5
Name
Order
Citations
PageRank
Dongha Lee1146.77
Su Kim200.34
Seonghyeon Lee301.35
Chanyoung Park416312.04
Hwanjo Yu51715114.02