Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion
Few-shot Knowledge Graph Completion (FKGC) has recently attracted significant research interest due to its ability to expand few-shot relation coverage in Knowledge Graphs. Prevailing FKGC approaches focus on exploiting the one-hop neighbor information of entities to enhance few-shot relation embedd...
Saved in:
Main Authors: | , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172789 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-172789 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1727892023-12-20T02:27:40Z Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion Li, Qianyu Yao, Jiale Tang, Xiaoli Yu, Han Jiang, Siyu Yang, Haizhi Song, Hengjie School of Computer Science and Engineering Engineering::Computer science and engineering Few-Shot Knowledge Graph Completion Knowledge Graph Few-shot Knowledge Graph Completion (FKGC) has recently attracted significant research interest due to its ability to expand few-shot relation coverage in Knowledge Graphs. Prevailing FKGC approaches focus on exploiting the one-hop neighbor information of entities to enhance few-shot relation embedding. However, these methods select one-hop neighbors randomly and neglect the rich multi-aspect information of entities. Although some methods have attempted to leverage Long Short-Term Memory (LSTM) to learn few-shot relation embedding, they are sensitive to the input order. To address these limitations, we propose the Capsule Neural Tensor Networks with Multi-Aspect Information approach (short for InforMix-FKGC). InforMix-FKGC employs a one-hop neighbor selection strategy based on how valuable they are and encodes multi-aspect information of entities, including one-hop neighbors, attributes and literal description. Then, a capsule network is responsible for integrating the support set and deriving few-shot relation embedding. Moreover, a neural tensor network is used to match the query set with the support set. In this way, InforMix-FKGC can learn few-shot relation embedding more precisely so as to enhance the accuracy of FKGC. Extensive experiments on the NELL-One and Wiki-One datasets demonstrate that InforMix-FKGC significantly outperforms ten state-of-the-art methods in terms of Mean Reciprocal Rank and Hits@K. Agency for Science, Technology and Research (A*STAR) Nanyang Technological University National Research Foundation (NRF) This work was supported, in part, by the National Natural Science Foundation of China [grant numbers 71671069]; the PreResearch Foundation of China [grant number 61400010205]; the National Key Research and Development Program of China [grant number 2018YFC0830900]; the National Research Foundation, Singapore under its the AI Singapore Programme [grant number AISG2-RP-2020-019]; the Joint NTU-WeBank Research Centre on Fintech [grant number NWJ-2020-008]; the RIE 2020 Advanced Manufacturing and Engineering Programmatic Fund [grant number A20G8b0102], Singapore; and the Nanyang Assistant Professorships (NAP). 2023-12-20T02:27:40Z 2023-12-20T02:27:40Z 2023 Journal Article Li, Q., Yao, J., Tang, X., Yu, H., Jiang, S., Yang, H. & Song, H. (2023). Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion. Neural Networks, 164, 323-334. https://dx.doi.org/10.1016/j.neunet.2023.04.041 0893-6080 https://hdl.handle.net/10356/172789 10.1016/j.neunet.2023.04.041 37163848 2-s2.0-85158838438 164 323 334 en AISG2-RP-2020-019 NWJ2020-008 A20G8b0102 Neural Networks © 2023 Elsevier Ltd. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Few-Shot Knowledge Graph Completion Knowledge Graph |
spellingShingle |
Engineering::Computer science and engineering Few-Shot Knowledge Graph Completion Knowledge Graph Li, Qianyu Yao, Jiale Tang, Xiaoli Yu, Han Jiang, Siyu Yang, Haizhi Song, Hengjie Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion |
description |
Few-shot Knowledge Graph Completion (FKGC) has recently attracted significant research interest due to its ability to expand few-shot relation coverage in Knowledge Graphs. Prevailing FKGC approaches focus on exploiting the one-hop neighbor information of entities to enhance few-shot relation embedding. However, these methods select one-hop neighbors randomly and neglect the rich multi-aspect information of entities. Although some methods have attempted to leverage Long Short-Term Memory (LSTM) to learn few-shot relation embedding, they are sensitive to the input order. To address these limitations, we propose the Capsule Neural Tensor Networks with Multi-Aspect Information approach (short for InforMix-FKGC). InforMix-FKGC employs a one-hop neighbor selection strategy based on how valuable they are and encodes multi-aspect information of entities, including one-hop neighbors, attributes and literal description. Then, a capsule network is responsible for integrating the support set and deriving few-shot relation embedding. Moreover, a neural tensor network is used to match the query set with the support set. In this way, InforMix-FKGC can learn few-shot relation embedding more precisely so as to enhance the accuracy of FKGC. Extensive experiments on the NELL-One and Wiki-One datasets demonstrate that InforMix-FKGC significantly outperforms ten state-of-the-art methods in terms of Mean Reciprocal Rank and Hits@K. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Li, Qianyu Yao, Jiale Tang, Xiaoli Yu, Han Jiang, Siyu Yang, Haizhi Song, Hengjie |
format |
Article |
author |
Li, Qianyu Yao, Jiale Tang, Xiaoli Yu, Han Jiang, Siyu Yang, Haizhi Song, Hengjie |
author_sort |
Li, Qianyu |
title |
Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion |
title_short |
Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion |
title_full |
Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion |
title_fullStr |
Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion |
title_full_unstemmed |
Capsule neural tensor networks with multi-aspect information for Few-shot Knowledge Graph Completion |
title_sort |
capsule neural tensor networks with multi-aspect information for few-shot knowledge graph completion |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/172789 |
_version_ |
1787136458513973248 |