A Few-Shot Knowledge Graph Completion Model With Neighbor Filter and Affine Attention
In recent times, extensive scholarly focus has been directed towards the knowledge graph completion (KGC) due to the large number of triples that perform well in training tasks. However, the relations of realistic knowledge graphs (KGs) usually have long-tailed distributions, posing a great challeng...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10840224/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590355877330944 |
|---|---|
| author | Hongfang Gong Yingjing Ding Minyi Ma |
| author_facet | Hongfang Gong Yingjing Ding Minyi Ma |
| author_sort | Hongfang Gong |
| collection | DOAJ |
| description | In recent times, extensive scholarly focus has been directed towards the knowledge graph completion (KGC) due to the large number of triples that perform well in training tasks. However, the relations of realistic knowledge graphs (KGs) usually have long-tailed distributions, posing a great challenge in inferring new triples of task relationships from a limited number of triples. To tackle this challenge, methodologies for few-shot knowledge graph completion (FKGC) have been devised. These approaches employ a limited set of reference triples to forecast novel triples for various relations. However, existing FKGC approaches suffer from the drawbacks of not fully utilizing the structural information in KGs and ignoring the fine-grained information of interactions between entity pairs. In this paper, a FKGC model with neighbor filter and affine attention (NFAA) is proposed. The NFAA model filters 2-hop neighbors into a neighborhood scope for an entity aggregator and constructs a relation generator utilizing the affine attention mechanism to efficiently infer new triples for the few-shot relation task. Evaluations are performed using two publicly available benchmark datasets: NELL-one and Wiki-one. Experimental results validate the superiority of the NFAA model relative to several state-of-the-art approaches. |
| format | Article |
| id | doaj-art-bed3e3acbd154c2d8c00be6ed186bdae |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-bed3e3acbd154c2d8c00be6ed186bdae2025-01-24T00:01:24ZengIEEEIEEE Access2169-35362025-01-0113123081232010.1109/ACCESS.2025.352952810840224A Few-Shot Knowledge Graph Completion Model With Neighbor Filter and Affine AttentionHongfang Gong0https://orcid.org/0000-0003-2618-9174Yingjing Ding1https://orcid.org/0009-0006-3805-7709Minyi Ma2https://orcid.org/0009-0008-7961-0464School of Mathematics and Statistics, Changsha University of Science and Technology, Changsha, ChinaSchool of Mathematics and Statistics, Changsha University of Science and Technology, Changsha, ChinaSchool of Mathematics and Statistics, Changsha University of Science and Technology, Changsha, ChinaIn recent times, extensive scholarly focus has been directed towards the knowledge graph completion (KGC) due to the large number of triples that perform well in training tasks. However, the relations of realistic knowledge graphs (KGs) usually have long-tailed distributions, posing a great challenge in inferring new triples of task relationships from a limited number of triples. To tackle this challenge, methodologies for few-shot knowledge graph completion (FKGC) have been devised. These approaches employ a limited set of reference triples to forecast novel triples for various relations. However, existing FKGC approaches suffer from the drawbacks of not fully utilizing the structural information in KGs and ignoring the fine-grained information of interactions between entity pairs. In this paper, a FKGC model with neighbor filter and affine attention (NFAA) is proposed. The NFAA model filters 2-hop neighbors into a neighborhood scope for an entity aggregator and constructs a relation generator utilizing the affine attention mechanism to efficiently infer new triples for the few-shot relation task. Evaluations are performed using two publicly available benchmark datasets: NELL-one and Wiki-one. Experimental results validate the superiority of the NFAA model relative to several state-of-the-art approaches.https://ieeexplore.ieee.org/document/10840224/Knowledge graph completionfew-shot knowledge graph completionattention mechanism |
| spellingShingle | Hongfang Gong Yingjing Ding Minyi Ma A Few-Shot Knowledge Graph Completion Model With Neighbor Filter and Affine Attention IEEE Access Knowledge graph completion few-shot knowledge graph completion attention mechanism |
| title | A Few-Shot Knowledge Graph Completion Model With Neighbor Filter and Affine Attention |
| title_full | A Few-Shot Knowledge Graph Completion Model With Neighbor Filter and Affine Attention |
| title_fullStr | A Few-Shot Knowledge Graph Completion Model With Neighbor Filter and Affine Attention |
| title_full_unstemmed | A Few-Shot Knowledge Graph Completion Model With Neighbor Filter and Affine Attention |
| title_short | A Few-Shot Knowledge Graph Completion Model With Neighbor Filter and Affine Attention |
| title_sort | few shot knowledge graph completion model with neighbor filter and affine attention |
| topic | Knowledge graph completion few-shot knowledge graph completion attention mechanism |
| url | https://ieeexplore.ieee.org/document/10840224/ |
| work_keys_str_mv | AT hongfanggong afewshotknowledgegraphcompletionmodelwithneighborfilterandaffineattention AT yingjingding afewshotknowledgegraphcompletionmodelwithneighborfilterandaffineattention AT minyima afewshotknowledgegraphcompletionmodelwithneighborfilterandaffineattention AT hongfanggong fewshotknowledgegraphcompletionmodelwithneighborfilterandaffineattention AT yingjingding fewshotknowledgegraphcompletionmodelwithneighborfilterandaffineattention AT minyima fewshotknowledgegraphcompletionmodelwithneighborfilterandaffineattention |