Structure Is All You Need: Structural Representation Learning on Hyper-Relational Knowledge Graphs
Jaejun Lee, Joyce Jiyoung Whang
Abstract
Hyper-relational knowledge graphs (HKGs) enrich knowledge graphs by extending a triplet to a hyper-relational fact, where a set of qualifiers adds auxiliary information to a triplet. While many HKG representation learning methods have been proposed, they often fail to effectively utilize the HKG's structure. This paper demonstrates that thoroughly leveraging the structure of an HKG is crucial for reasoning on HKGs, and a purely structure-based representation learning method can achieve state-of-the-art performance on various link prediction tasks. We propose MAYPL, which learns to initialize representation vectors based on the structure of an HKG and employs an attentive neural message passing consisting of fact-level message computation and entity-centric and relation-centric aggregations, thereby computing the representations based solely on the structure. Due to its structure-driven learning, MAYPL can conduct inductive inferences on new entities and relations. MAYPL outperforms 40 knowledge graph completion methods in 10 datasets, compared with different baseline methods on different datasets to be tested from diverse perspectives.
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.
1 top-tier paper has 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
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction cites Inductive Relation Prediction by Subgraph Reasoning
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction cites Composition-based Multi-Relational Graph Convolutional Networks
- Knowledge Graph Reasoning with Relational Digraph cites Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
- Knowledge Graph Reasoning with Relational Digraph cites Inductive Relation Prediction by Subgraph Reasoning
- Knowledge Graph Reasoning with Relational Digraph cites Composition-based Multi-Relational Graph Convolutional Networks
Cited by top-tier papers1
Builds on26
- How Attentive are Graph Attention Networks?Shaked Brody, Uri Alon, Eran YahavICLR 2022 · 1,717 citations
- Composition-based Multi-Relational Graph Convolutional NetworksShikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha P. TalukdarICLR 2020 · 1,105 citations
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link PredictionZhaocheng Zhu, Zuobai Zhang, Louis-Pascal A. C. Xhonneux, Jian TangNeurIPS 2021 · 546 citations
- Inductive Relation Prediction by Subgraph ReasoningKomal K. Teru, Etienne G. Denis, William L. HamiltonICML 2020 · 493 citations
- Knowledge Graph Reasoning with Relational DigraphYongqi Zhang, Quanming YaoWWW 2022 · 193 citations
Related papers
- Hyper-Relational Knowledge Representation Learning with Multi-Hypergraph DisentanglementJiecheng Li, Xudong Luo, Guangquan Lu, Shichao ZhangWWW 2025 · 4 citations
- Query Embedding on Hyper-Relational Knowledge GraphsDimitrios Alivanistos, Max Berrendorf, Michael Cochez, Mikhail GalkinICLR 2022 · 29 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
- Beyond Triplets: Hyper-Relational Knowledge Graph Embedding for Link PredictionPaolo Rosso, Dingqi Yang, Philippe Cudré-MaurouxWWW 2020 · 158 citations
- Message Passing for Hyper-Relational Knowledge GraphsMikhail Galkin, Priyansh Trivedi, Gaurav Maheshwari, Ricardo Usbeck et al.EMNLP 2020 · 17 citations
