HyperGCN: A new method of training graph convolutional networks on hypergraphs

Yadati, N and Yadav, P and Louis, A and Nimishakavi, M and Nitin, V and Talukdar, P (2019) HyperGCN: A new method of training graph convolutional networks on hypergraphs. In: 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019, 8 - 14 December 2019, Vancouver.

PDF NIPS_2019.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

In many real-world networks such as co-authorship, co-citation, etc., relationships are complex and go beyond pairwise associations. Hypergraphs provide a flexible and natural modeling tool to model such complex relationships. The obvious existence of such complex relationships in many real-world networks naturally motivates the problem of learning with hypergraphs. A popular learning paradigm is hypergraph-based semi-supervised learning (SSL) where the goal is to assign labels to initially unlabelled vertices in a hypergraph. Motivated by the fact that a graph convolutional network (GCN) has been effective for graph-based SSL, we propose HyperGCN, a novel way of training a GCN for SSL on hypergraphs based on tools from sepctral theory of hypergraphs. We demonstrate HyperGCN's effectiveness through detailed experimentation on real-world hypergraphs for SSL and combinatorial optimisation and analyse when it is going to be more effective than state-of-the art baselines. We have made the source code available.

Item Type:	Conference Paper
Publication:	Advances in Neural Information Processing Systems
Publisher:	Neural information processing systems foundation
Additional Information:	The copyright for this article belongs to Neural information processing systems foundation.
Keywords:	Combinatorial optimization; Complex networks; Convolution; Convolutional neural networks; Graphic methods; Semi-supervised learning, Co-authorships; Complex relationships; Convolutional networks; Learning paradigms; Natural models; Real-world networks; Semi-supervised learning (SSL); State of the art, Graph theory
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	02 Dec 2022 09:17
Last Modified:	02 Dec 2022 09:17
URI:	https://eprints.iisc.ac.in/id/eprint/78177

Actions (login required)

View Item