Uniform pooling for graph networks
|Author:||Qin, Jian1; Liu, Li2,3; Shen, Hui2;|
1The College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
2The College of System Engineering, National University of Defense Technology, Changsha 410073, China
3The Center for Machine Vision and Signal Analysis, University of Oulu, 90014 Oulu, Finland
|Online Access:||PDF Full Text (PDF, 0.7 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2020120399204
Multidisciplinary Digital Publishing Institute,
|Publish Date:|| 2020-12-03
The graph convolution network has received a lot of attention because it extends the convolution to non-Euclidean domains. However, the graph pooling method is still less concerned, which can learn coarse graph embedding to facilitate graph classification. Previous pooling methods were based on assigning a score to each node and then pooling only the highest-scoring nodes, which might throw away whole neighbourhoods of nodes and therefore information. Here, we proposed a novel pooling method UGPool with a new point-of-view on selecting nodes. UGPool learns node scores based on node features and uniformly pools neighboring nodes instead of top nodes in the score-space, resulting in a uniformly coarsened graph. In multiple graph classification tasks, including the protein graphs, the biological graphs and the brain connectivity graphs, we demonstrated that UGPool outperforms other graph pooling methods while maintaining high efficiency. Moreover, we also show that UGPool can be integrated with multiple graph convolution networks to effectively improve performance compared to no pooling.
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
113 Computer and information sciences
This research was funded by the National Natural Science Foundation of China (grant numbers 61773391 and 61722313), the National Key Research and Development Program (2018YFB1305101), and the Science and Technology Innovation Program of Hunan Province (2018RS3080).
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).