# Inductive Link Prediction on N-ary Relational Facts via Semantic Hypergraph Reasoning

arXiv: https://arxiv.org/abs/2503.20676 · HTML: https://mlsanity.com/paper/2503.20676/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 26 of 26)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Recipe for a General, Powerful, Scalable Graph Transformer](https://mlsanity.com/paper/2205.12454/) (2022)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Representing Long-Range Context for Graph Neural Networks with Global Attention](https://mlsanity.com/paper/2201.08821/) (2022)
- [DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs](https://mlsanity.com/paper/1911.00055/) (2019)
- [UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks](https://mlsanity.com/paper/2105.00956/) (2021)
- [HNHN: Hypergraph Networks with Hyperedge Neurons](https://mlsanity.com/paper/2006.12278/) (2020)
- [Knowledge Graph Embedding for Link Prediction: A Comparative Analysis](https://mlsanity.com/paper/2002.00819/) (2020)
- [Message Passing for Hyper-Relational Knowledge Graphs](https://mlsanity.com/paper/2009.10847/) (2020)
- [NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs](https://mlsanity.com/paper/2106.12144/) (2021)
- [Inductive Entity Representations from Text via Link Prediction](https://mlsanity.com/paper/2010.03496/) (2020)
- [On the representation and embedding of knowledge bases beyond binary relations](https://mlsanity.com/paper/1604.08642/) (2016)
- [Communicative Message Passing for Inductive Relation Reasoning](https://mlsanity.com/paper/2012.08911/) (2020)
- [Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/2103.03642/) (2021)
- [Role-Aware Modeling for N-ary Relational Knowledge Bases](https://mlsanity.com/paper/2104.09780/) (2021)
- [Link Prediction on N-ary Relational Facts: A Graph-based Approach](https://mlsanity.com/paper/2105.08476/) (2021)
- [On Structural Expressive Power of Graph Transformers](https://mlsanity.com/paper/2305.13987/) (2023)
- [Improving Hyper-Relational Knowledge Graph Completion](https://mlsanity.com/paper/2104.08167/) (2021)
- [Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers](https://mlsanity.com/paper/2305.18256/) (2023)
- [Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs](https://mlsanity.com/paper/2302.01859/) (2023)
- [HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level](https://mlsanity.com/paper/2305.06588/) (2023)
- [Link Prediction with Relational Hypergraphs](https://mlsanity.com/paper/2402.04062/) (2024)
- [Understanding Expressivity of GNN in Rule Learning](https://mlsanity.com/paper/2303.12306/) (2023)
- [HyperFormer: Enhancing Entity and Relation Interaction for Hyper-Relational Knowledge Graph Completion](https://mlsanity.com/paper/2308.06512/) (2023)

## Built on by (most cited first, 3 of 3)

- [A Survey of Link Prediction in N-ary Knowledge Graphs](https://mlsanity.com/paper/2506.08970/) (2025)
- [THOR: Inductive Link Prediction over Hyper-Relational Knowledge Graphs](https://mlsanity.com/paper/2602.05424/) (2026)
- [HEHRGNN: A Unified Embedding Model for Knowledge Graphs with Hyperedges and Hyper-Relational Edges](https://mlsanity.com/paper/2602.18897/) (2026)

## Abstract (arXiv)

N-ary relational facts represent semantic correlations among more than two entities. While recent studies have developed link prediction (LP) methods to infer missing relations for knowledge graphs (KGs) containing n-ary relational facts, they are generally limited to transductive settings. Fully inductive settings, where predictions are made on previously unseen entities, remain a significant challenge. As existing methods are mainly entity embedding-based, they struggle to capture entity-independent logical rules. To fill in this gap, we propose an n-ary subgraph reasoning framework for fully inductive link prediction (ILP) on n-ary relational facts. This framework reasons over local subgraphs and has a strong inductive inference ability to capture n-ary patterns. Specifically, we introduce a novel graph structure, the n-ary semantic hypergraph, to facilitate subgraph extraction. Moreover, we develop a subgraph aggregating network, NS-HART, to effectively mine complex semantic correlations within subgraphs. Theoretically, we provide a thorough analysis from the score function optimization perspective to shed light on NS-HART's effectiveness for n-ary ILP tasks. Empirically, we conduct extensive experiments on a series of inductive benchmarks, including transfer reasoning (with and without entity features) and pairwise subgraph reasoning. The results highlight the superiority of the n-ary subgraph reasoning framework and the exceptional inductive ability of NS-HART. The source code of this paper has been made publicly available at https://github.com/yin-gz/Nary-Inductive-SubGraph.