Mutual Information Maximization in Graph Neural Networks
release_pj3zvlsykndjflw6louwy3bw44
by
Xinhan Di, Pengqian Yu, Rui Bu, Mingchao Sun
2020
Abstract
A variety of graph neural networks (GNNs) frameworks for representation
learning on graphs have been recently developed. These frameworks rely on
aggregation and iteration scheme to learn the representation of nodes. However,
information between nodes is inevitably lost in the scheme during learning. In
order to reduce the loss, we extend the GNNs frameworks by exploring the
aggregation and iteration scheme in the methodology of mutual information. We
propose a new approach of enlarging the normal neighborhood in the aggregation
of GNNs, which aims at maximizing mutual information. Based on a series of
experiments conducted on several benchmark datasets, we show that the proposed
approach improves the state-of-the-art performance for four types of graph
tasks, including supervised and semi-supervised graph classification, graph
link prediction and graph edge generation and classification.
In text/plain
format
Archived Files and Locations
application/pdf 153.0 kB
file_uyefr2xk3ffydbsldwmcvf3674
|
arxiv.org (repository) web.archive.org (webarchive) |
1905.08509v4
access all versions, variants, and formats of this works (eg, pre-prints)