HyConvE: A Novel Embedding Model for Knowledge Hypergraph Link Prediction with Convolutional Neural Networks
Open Access
- 30 April 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 188-198
Abstract
Knowledge hypergraph embedding, which projects entities and n-ary relations into a low-dimensional continuous vector space to predict missing links, remains a challenging area to be explored despite the ubiquity of n-ary relational facts in the real world. Currently, knowledge hypergraph link prediction methods are essentially simple extensions of those used in knowledge graphs, where n-ary relational facts are decomposed into different subelements. Convolutional neural networks have been shown to have remarkable information extraction capabilities in previous work on knowledge graph link prediction. In this paper, we propose a novel embedding-based knowledge hypergraph link prediction model named HyConvE, which exploits the powerful learning ability of convolutional neural networks for effective link prediction. Specifically, we employ 3D convolution to capture the deep interactions of entities and relations to efficiently extract explicit and implicit knowledge in each n-ary relational fact without compromising its translation property. In addition, appropriate relation and position-aware filters are utilized sequentially to perform two-dimensional convolution operations to capture the intrinsic patterns and position information in each n-ary relation, respectively. Extensive experimental results on real datasets of knowledge hypergraphs and knowledge graphs demonstrate the superior performance of HyConvE compared with state-of-the-art baselines.Keywords
Funding Information
- National Natural Science Foundation of China (61972275)
- Australian Research Council (LP180100750)
- Ministry of Science and Technology of the People's Republic of China (2020AAA0108504)
This publication has 18 references indexed in Scilit:
- Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases2020
- InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature InteractionsProceedings of the AAAI Conference on Artificial Intelligence, 2020
- AutoSF: Searching Scoring Functions for Knowledge Graph Embedding2020
- Link Prediction on N-ary Relational Data2019
- Adaptive Convolution for Multi-Relational Learning2019
- Scalable Instance Reconstruction in Knowledge Bases via Relatedness Affiliated Embedding2018
- Weakly-supervised Relation Extraction by Pattern-enhanced Embedding Learning2018
- Representing Text for Joint Embedding of Text and Knowledge Bases2015
- WikidataCommunications of the ACM, 2014
- Freebase2008