ACL Findings2021
Link Prediction on N-ary Relational Facts: A Graph-based Approach
Quan Wang, Haifeng Wang, Yajuan Lyu, Yong Zhu
Abstract
Link prediction on knowledge graphs (KGs) is a key research topic. Previous work mainly focused on binary relations, paying less attention to higher-arity relations although they are ubiquitous in real-world KGs. This paper considers link prediction upon n-ary relational facts and proposes a graph-based approach to this task. The key to our approach is to represent the nary structure of a fact as a small heterogeneous graph, and model this graph with edge-biased fully-connected attention. The fully-connected attention captures universal inter-vertex interactions, while with edge-aware attentive biases to particularly encode the graph structure and its heterogeneity. In this fashion, our approach fully models global and local dependencies in each n-ary fact, and hence can more effectively capture associations therein. Extensive evaluation verifies the effectiveness and superiority of our approach. It performs substantially and consistently better than current state-of-the-art across a variety of n-ary relational benchmarks. Our code is publicly available. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
14 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation cites Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation cites Beyond Triplets: Hyper-Relational Knowledge Graph Embedding for Link Prediction
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation cites Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction
- Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers cites HittER: Hierarchical Transformers for Knowledge Graph Embeddings
- Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers cites Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases
- Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers cites Beyond Triplets: Hyper-Relational Knowledge Graph Embedding for Link Prediction
- Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers cites Role-Aware Modeling for N-ary Relational Knowledge Bases
- Shrinking Embeddings for Hyper-Relational Knowledge Graphs cites Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases
- Shrinking Embeddings for Hyper-Relational Knowledge Graphs cites Beyond Triplets: Hyper-Relational Knowledge Graph Embedding for Link Prediction
- DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typing cites Beyond Triplets: Hyper-Relational Knowledge Graph Embedding for Link Prediction
- Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction cites Beyond Triplets: Hyper-Relational Knowledge Graph Embedding for Link Prediction
- Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction cites Role-Aware Modeling for N-ary Relational Knowledge Bases
- Role-Aware Modeling for N-ary Relational Knowledge Bases cites Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases
- Role-Aware Modeling for N-ary Relational Knowledge Bases cites Beyond Triplets: Hyper-Relational Knowledge Graph Embedding for Link Prediction
Cited by top-tier papers14
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge RepresentationHaoran Luo, Haihong E, Guanting Chen, Yandan Zheng et al.NeurIPS 2025 · 81 citations
- Shrinking Embeddings for Hyper-Relational Knowledge GraphsBo Xiong, Mojtaba Nayyeri, Shirui Pan, Steffen StaabACL 2023 · 19 citations
- Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph ConstructionHaoran Luo, Haihong E, Yuhao Yang, Tianyu Yao et al.NeurIPS 2024 · 19 citations
- DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity TypingHaoran Luo, Haihong E, Ling Tan, Gengxian Zhou et al.AAAI 2023 · 18 citations
- Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with TransformersChanyoung Chung, Jaejun Lee, Joyce Jiyoung WhangKDD 2023 · 14 citations
Builds on7
- Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation ExtractionBenfeng Xu, Quan Wang, Yajuan Lyu, Yong Zhu et al.AAAI 2021 · 200 citations
- Beyond Triplets: Hyper-Relational Knowledge Graph Embedding for Link PredictionPaolo Rosso, Dingqi Yang, Philippe Cudré-MaurouxWWW 2020 · 158 citations
- HittER: Hierarchical Transformers for Knowledge Graph EmbeddingsSanxing Chen, Xiaodong Liu, Jianfeng Gao, Jian Jiao et al.EMNLP 2021 · 110 citations
- Generalizing Tensor Decomposition for N-ary Relational Knowledge BasesYu Liu, Quanming Yao, Yong LiWWW 2020 · 91 citations
- Role-Aware Modeling for N-ary Relational Knowledge BasesYu Liu, Quanming Yao, Yong LiWWW 2021 · 72 citations
Related papers
- A Survey of Link Prediction in N-ary Knowledge GraphsJiyao Wei, Saiping Guan, Da Li, Zhongni Hou et al.EMNLP 2025 · 1 citation
- Inductive Link Prediction on N-ary Relational Facts via Semantic Hypergraph ReasoningGongzhu Yin, Hongli Zhang, Yuchen Yang, Yi LuoKDD 2025
- HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local LevelHaoran Luo, Haihong E, Yuhao Yang, Yikai Guo et al.ACL 2023 · 11 citations
- Fact-Tree Reasoning for N-ary Question Answering over Knowledge GraphsYao Zhang, Peiyao Li, Hongru Liang, Adam Jatowt et al.ACL Findings 2022 · 5 citations
- Joint Global-Local Representations via Relation-Entity Pair Encoding for Hyper-Relational Knowledge GraphsSangjun Ji, Sangjune Kim, Youngho Lee, Bonyou Koo et al.KDD 2026
