Modelling Multi-relations for Convolutional-based Knowledge Graph Embedding

Sirui Li; Kevin Wong; Dengya Zhu; Lance Chun Che Fung

doi:10.1016/j.procs.2022.09.117

Back

Modelling Multi-relations for Convolutional-based Knowledge Graph Embedding

Journal article

Open access

Peer reviewed

Modelling Multi-relations for Convolutional-based Knowledge Graph Embedding

Sirui Li, Kevin Wong, Dengya Zhu and Lance Chun Che Fung

Procedia computer science, Vol.207, pp.624-633

26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (Verona, Italy, 07/09/2022–09/09/2022)

2022

DOI: https://doi.org/10.1016/j.procs.2022.09.117

Files and links (1)

pdf

Published415.33 kBDownload View

CC BY-NC-ND V4.0, Open Access

Abstract

Knowledge Graph Embedding

Multi-relation

Convolution

Representation learning

Representation learning of knowledge graphs aims to embed entities and relations into low-dimensional vectors. Most existing works only consider the direct relations or paths between an entity pair. It is considered that such approaches disconnect the semantic connection of multi-relations between an entity pair, and we propose a convolutional and multi-relational representation learning model, ConvMR. The proposed ConvMR model addresses the multi-relation issue in two aspects: (1) Encoding the multi-relations between an entity pair into a unified vector that maintains the semantic connection. (2) Since not all relations are necessary while joining multi-relations, we propose an attention-based relation encoder to automatically assign weights to different relations based on semantic hierarchy. Experimental results on two popular datasets, FB15k-237 and WN18RR, achieved consistent improvements on the mean rank. We also found that ConvMR is efficient to deal with less frequent entities.

Details

Title: Modelling Multi-relations for Convolutional-based Knowledge Graph Embedding
Authors/Creators: Sirui Li - Murdoch University, School of Information Technology
Kevin Wong - Murdoch University, Centre for Water, Energy and Waste
Dengya Zhu - Curtin University
Lance Chun Che Fung
Publication Details: Procedia computer science, Vol.207, pp.624-633
Conference: 26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (Verona, Italy, 07/09/2022–09/09/2022)
Publisher: Elsevier B.V.
Identifiers: 991005693763807891
Murdoch Affiliation: School of Information Technology; Centre for Water, Energy and Waste
Language: English
Resource Type: Journal article
Note: Paper presented at the 26th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2022)

Metrics

41 Record Views