mlsanityData to 14 Oct 2026

HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs

arXiv 2506.12362 ↗First posted 14 Jun 2025cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Inductive link prediction with knowledge hypergraphs is the task of predicting missing hyperedges involving completely novel entities (i.e., nodes unseen during training). Existing methods for inductive link prediction with knowledge hypergraphs assume a fixed relational vocabulary and, as a result, cannot generalize to knowledge hypergraphs with novel relation types (i.e., relations unseen during training). Inspired by knowledge graph foundation models, we propose HYPER as a foundation model for link prediction, which can generalize to any knowledge hypergraph, including novel entities and novel relations. Importantly, HYPER can learn and transfer across different relation types of varying arities, by encoding the entities of each hyperedge along with their respective positions in the hyperedge. To evaluate HYPER, we construct 16 new inductive datasets from existing knowledge hypergraphs, covering a diverse range of relation types of varying arities. Empirically, HYPER consistently outperforms all existing methods in both node-only and node-and-relation inductive settings, showing strong generalization to unseen, higher-arity relational structures.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 36 of its 46 references that are in the map. First posted on arXiv 14 Jun 2025.

Builds on

36 of 46 references.

References · 36

  1. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  2. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  3. 2016Complex Embeddings for Simple Link Predictioncited by 902
  4. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  5. 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
  6. 2018Hypergraph Neural Networkscited by 488
  7. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 396
  8. 2019TuckER: Tensor Factorization for Knowledge Graph Completioncited by 290
  9. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 275
  10. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 239
  11. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 149
  12. 2020BoxE: A Box Embedding Model for Knowledge Base Completioncited by 105
24 more
  1. 2020CoDEx: A Comprehensive Knowledge Graph Completion Benchmarkcited by 102
  2. 2021Knowledge Graph Reasoning with Relational Digraphcited by 92
  3. 2023Towards Foundation Models for Knowledge Graph Reasoningcited by 86
  4. 2024Position: Graph Foundation Models are Already Herecited by 86
  5. 2020Message Passing for Hyper-Relational Knowledge Graphscited by 79
  6. 2021NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphscited by 72
  7. 2016On the representation and embedding of knowledge bases beyond binary relationscited by 55
  8. 2023InGram: Inductive Knowledge Graph Embedding via Relation Graphscited by 52
  9. 2022A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphscited by 49
  10. 2023A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphscited by 32
  11. 2022AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoningcited by 28
  12. 2024A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoningcited by 25
  13. 2023A Multi-Task Perspective for Link Prediction with New Relation Types and Nodescited by 24
  14. 2025TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphscited by 24
  15. 2025How Expressive are Knowledge Graph Foundation Models?cited by 23
  16. 2023Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Typescited by 21
  17. 2021Link Prediction on N-ary Relational Data Based on Relatedness Evaluationcited by 15
  18. 2022RAILD: Towards Leveraging Relation Features for Inductive Link Prediction In Knowledge Graphscited by 12
  19. 2021Hypergraph Pre-training with Graph Neural Networkscited by 9
  20. 2024Link Prediction with Relational Hypergraphscited by 9
  21. 2024HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphscited by 7
  22. 2025Hypergraph Foundation Modelcited by 5
  23. 2024Instruction-based Hypergraph Pretrainingcited by 2
  24. 2023Self-Supervised Pretraining for Heterogeneous Hypergraph Neural Networkscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026RelAgent: LLM Agents as Data Scientists for Relational Learningcited by 2
  2. 2026UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAGcited by 0
  3. 2026A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networkscited by 0
  4. 2026α-Graph: Attention-Infused Normalizing Flow Approach to Tractable Graph Modelingcited by 0
  5. 2026Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNscited by 0
  6. 2026HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoningcited by 0
  7. 2026The Universal Classifier for Graph Learningcited by 0