Neural message passing for multi-relational ordered and recursive hypergraphs

Yadati, N (2020) Neural message passing for multi-relational ordered and recursive hypergraphs. In: Advances in Neural Information Processing Systems, 6 December - 12 December 2020, Virtual, Online.

PDF NeurIPS_2020 - Published Version Restricted to Registered users only Download (844kB) | Request a copy

Abstract

Message passing neural network (MPNN) has recently emerged as a successful framework by achieving state-of-the-art performances on many graph-based learning tasks. MPNN has also recently been extended to multi-relational graphs (each edge is labelled), and hypergraphs (each edge can connect any number of vertices). However, in real-world datasets involving text and knowledge, relationships are much more complex in which hyperedges can be multi-relational, recursive, and ordered. Such structures present several unique challenges because it is not clear how to adapt MPNN to variable-sized hyperedges in them. In this work, we first unify exisiting MPNNs on different structures into G-MPNN (Generalised-MPNN) framework. Motivated by real-world datasets, we then propose a novel extension of the framework, MPNN-R (MPNN-Recursive) to handle recursively-structured data. Experimental results demonstrate the effectiveness of proposed instances of G-MPNN and MPNN-R. The code is 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:	Graph structures; Graph theory; Graphic methods, Different structure; Graph-based learning; Hyper graph; Hyperedges; Real-world datasets; Relational graph; State-of-the-art performance; Structured data, Message passing
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	07 Feb 2023 04:55
Last Modified:	07 Feb 2023 04:55
URI:	https://eprints.iisc.ac.in/id/eprint/79984

Actions (login required)

View Item