Hybrid attention mechanism for few‐shot relational learning of knowledge graphs
Open Access
- 8 September 2021
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 15 (8), 561-572
- https://doi.org/10.1049/cvi2.12066
Abstract
Few-shot knowledge graph (KG) reasoning is the main focus in the field of knowledge graph reasoning. In order to expand the application fields of the knowledge graph, a large number of studies are based on a large number of training samples. However, we have learnt that there are actually many missing relationships or entities in the knowledge graph, and in most cases, there are not many training instances when implementing new relationships. To tackle it, in this study, the authors aim to predict a new entity given few reference instances, even only one training instance. A few-shot learning framework based on a hybrid attention mechanism is proposed. The framework employs traditional embedding models to extract knowledge, and uses an attenuated attention network and a self-attention mechanism to obtain the hidden attributes of entities. Thus, it can learn a matching metric by considering both the learnt embeddings and one-hop graph structures. The experimental results present that the model has achieved significant performance improvements on the NELL-One and Wiki-One datasets.Keywords
Funding Information
- Natural Science Foundation of Liaoning Province (2020‐BS‐063)
- National Natural Science Foundation of China (61906030)
This publication has 19 references indexed in Scilit:
- Modeling Relational Data with Graph Convolutional NetworksPublished by Springer Science and Business Media LLC ,2018
- Never-ending learningCommunications of the ACM, 2018
- Diverse Few-Shot Text Classification with Multiple MetricsPublished by Association for Computational Linguistics (ACL) ,2018
- Knowledge Graph Embedding: A Survey of Approaches and ApplicationsIEEE Transactions on Knowledge and Data Engineering, 2017
- Representing Text for Joint Embedding of Text and Knowledge BasesPublished by Association for Computational Linguistics (ACL) ,2015
- Modeling Relation Paths for Representation Learning of Knowledge BasesPublished by Association for Computational Linguistics (ACL) ,2015
- WikidataCommunications of the ACM, 2014
- ProbasePublished by Association for Computing Machinery (ACM) ,2012
- FreebasePublished by Association for Computing Machinery (ACM) ,2008
- DBpedia: A Nucleus for a Web of Open DataLecture Notes in Computer Science, 2007