UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Learning Discrete Structures for Graph Neural Networks

Franceschi, L; Niepert, M; Pontil, M; He, X; (2019) Learning Discrete Structures for Graph Neural Networks. In: Chaudhuri,, Kamalika and Salakhutdinov, Ruslan, (eds.) Proceedings of International Conference on Machine Learning - 2019. PMLR: Long Beach, California, USA. Green open access

[thumbnail of franceschi19a.pdf]
Preview
Text
franceschi19a.pdf - Published Version

Download (2MB) | Preview

Abstract

Graph neural networks (GNNs) are a popular class of machine learning models whose major advantage is their ability to incorporate a sparse and discrete dependency structure between data points. Unfortunately, GNNs can only be used when such a graph-structure is available. In practice, however, real-world graphs are often noisy and incomplete or might not be available at all. With this work, we propose to jointly learn the graph structure and the parameters of graph convolutional networks (GCNs) by approximately solving a bilevel program that learns a discrete probability distribution on the edges of the graph. This allows one to apply GCNs not only in scenarios where the given graph is incomplete or corrupted but also in those where a graph is not available. We conduct a series of experiments that analyze the behavior of the proposed method and demonstrate that it outperforms related methods by a significant margin.

Type: Proceedings paper
Title: Learning Discrete Structures for Graph Neural Networks
Event: International Conference on Machine Learning - 2019
Open access status: An open access version is available from UCL Discovery
Publisher version: http://proceedings.mlr.press/v97/franceschi19a/fra...
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10077010
Downloads since deposit
70Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item