Murdoch University Research Repository

Welcome to the Murdoch University Research Repository

The Murdoch University Research Repository is an open access digital collection of research
created by Murdoch University staff, researchers and postgraduate students.

Learn more

Structure-Feature based Graph Self-adaptive Pooling

Zhang, L., Wang, X., Li, H., Zhu, G., Shen, P., Li, P., Lu, X., Shah, S.A.A. and Bennamoun, M. (2020) Structure-Feature based Graph Self-adaptive Pooling. In: 29th International World Wide Web Conference (WWW 2020), 20 - 24 April 2020, Taipei, Taiwan

Free to read: https://doi.org/10.1145/3366423.3380083
*No subscription required

Abstract

Various methods to deal with graph data have been proposed in recent years. However, most of these methods focus on graph feature aggregation rather than graph pooling. Besides, the existing top-k selection graph pooling methods have a few problems. First, to construct the pooled graph topology, current top-k selection methods evaluate the importance of the node from a single perspective only, which is simplistic and unobjective. Second, the feature information of unselected nodes is directly lost during the pooling process, which inevitably leads to a massive loss of graph feature information. To solve these problems mentioned above, we propose a novel graph self-adaptive pooling method with the following objectives: (1) to construct a reasonable pooled graph topology, structure and feature information of the graph are considered simultaneously, which provide additional veracity and objectivity in node selection; and (2) to make the pooled nodes contain sufficiently effective graph information, node feature information is aggregated before discarding the unimportant nodes; thus, the selected nodes contain information from neighbor nodes, which can enhance the use of features of the unselected nodes. Experimental results on four different datasets demonstrate that our method is effective in graph classification and outperforms state-of-the-art graph pooling methods.

Item Type: Conference Paper
Murdoch Affiliation: Information Technology, Mathematics and Statistics
URI: http://researchrepository.murdoch.edu.au/id/eprint/56609
Item Control Page Item Control Page