Few-shot Link Prediction on N-ary Facts
Not on the map. Why?
Abstract (arXiv)
Hyper-relational facts, which consist of a primary triple (head entity, relation, tail entity) and auxiliary attribute-value pairs, are widely present in real-world Knowledge Graphs (KGs). Link Prediction on Hyper-relational Facts (LPHFs) is to predict a missing element in a hyper-relational fact, which helps populate and enrich KGs. However, existing LPHFs studies usually require an amount of high-quality data. They overlook few-shot relations, which have limited instances, yet are common in real-world scenarios. Thus, we introduce a new task, Few-Shot Link Prediction on Hyper-relational Facts (FSLPHFs). It aims to predict a missing entity in a hyper-relational fact with limited support instances. To tackle FSLPHFs, we propose MetaRH, a model that learns Meta Relational information in Hyper-relational facts. MetaRH comprises three modules: relation learning, support-specific adjustment, and query inference. By capturing meta relational information from limited support instances, MetaRH can accurately predict the missing entity in a query. As there is no existing dataset available for this new task, we construct three datasets to validate the effectiveness of MetaRH. Experimental results on these datasets demonstrate that MetaRH significantly outperforms existing representative models.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 42 references that are in the map. First posted on arXiv 10 May 2023.
Builds on
20 of 42 references.
References · 20
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
- 2019TuckER: Tensor Factorization for Knowledge Graph Completioncited by 290
- 2017Meta Networkscited by 269
- 2018SimplE Embedding for Link Prediction in Knowledge Graphscited by 195
- 2020BoxE: A Box Embedding Model for Knowledge Base Completioncited by 105
- 2020Message Passing for Hyper-Relational Knowledge Graphscited by 79
- 2018One-Shot Relational Learning for Knowledge Graphscited by 78
- 2019Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphscited by 73
- 2019Few-Shot Knowledge Graph Completioncited by 63
8 more
- 2016On the representation and embedding of knowledge bases beyond binary relationscited by 55
- 2020Adaptive Attentional Network for Few-Shot Knowledge Graph Completioncited by 42
- 2020Generalizing Tensor Decomposition for N-ary Relational Knowledge Basescited by 38
- 2021Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completioncited by 32
- 2021Link Prediction on N-ary Relational Facts: A Graph-based Approachcited by 29
- 2021Link Prediction on N-ary Relational Data Based on Relatedness Evaluationcited by 15
- 2021Searching to Sparsify Tensor Decomposition for N-ary Relational Datacited by 13
- 2019Knowledge Hypergraphs: Prediction Beyond Binary Relationscited by 3
Built on by
Citing papers per year: 2026: 2.
2 papers.