NHP: Neural Hypergraph Link Prediction

Yadati, N and Nitin, V and Nimishakavi, M and Yadav, P and Louis, A and Talukdar, P (2020) NHP: Neural Hypergraph Link Prediction. In: 29th ACM International Conference on Information and Knowledge Management, 19-23 oct 2020, Virtual, Online, pp. 1705-1714.

PDF CIKM 2020 - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Link prediction insimple graphs is a fundamental problem in which new links between vertices are predicted based on the observed structure of the graph. However, in many real-world applications, there is a need to model relationships among vertices that go beyond pairwise associations. For example, in a chemical reaction, relationship among the reactants and products is inherently higher-order. Additionally, there is a need to represent the direction from reactants to products. Hypergraphs provide a natural way to represent such complex higher-order relationships. Graph Convolutional Network (GCN) has recently emerged as a powerful deep learning-based approach for link prediction over simple graphs. However, their suitability for link prediction in hypergraphs is underexplored - we fill this gap in this paper and propose Neural Hyperlink Predictor (NHP). NHP adapts GCNs for link prediction in hypergraphs. We propose two variants of NHP - NHP-U and NHP-D - for link prediction over undirected and directed hypergraphs, respectively. To the best of our knowledge, NHP-D is the first-ever method for link prediction over directed hypergraphs. An important feature of NHP is that it can also be used for hyperlinks in which dissimilar vertices interact (e.g. acids reacting with bases). Another attractive feature of NHP is that it can be used to predict unseen hyperlinks at test time (inductive hyperlink prediction). Through extensive experiments on multiple real-world datasets, we show NHP's effectiveness. © 2020 ACM.

Item Type:	Conference Paper
Publication:	International Conference on Information and Knowledge Management, Proceedings
Publisher:	Association for Computing Machinery
Additional Information:	this copyright for this article belongs to International Conference on Information and Knowledge Management
Keywords:	Convolutional neural networks; Deep learning; Forecasting; Hypertext systems; Knowledge management, Convolutional networks; Directed hypergraphs; Higher-order; Important features; Learning-based approach; Link prediction; Model relationships; Real-world datasets, Graph theory
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	31 Dec 2021 05:14
Last Modified:	31 Dec 2021 05:14
URI:	http://eprints.iisc.ac.in/id/eprint/67357

Actions (login required)

View Item