HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs
- URL: http://arxiv.org/abs/2506.12362v1
- Date: Sat, 14 Jun 2025 05:53:49 GMT
- Title: HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs
- Authors: Xingyue Huang, Mikhail Galkin, Michael M. Bronstein, İsmail İlkan Ceylan,
- Abstract summary: We propose HYPER as a foundation model for link prediction, which can generalize to any knowledge hypergraph.<n> HYPER can learn and transfer across different relation types of varying arities, by encoding the entities of each hyperedge.<n> Empirically, HYPER consistently outperforms all existing methods in both node-only and node-and-relation inductive settings.
- Score: 25.99060678469887
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- EntailE: Introducing Textual Entailment in Commonsense Knowledge Graph
Completion [54.12709176438264]
Commonsense knowledge graphs (CSKGs) utilize free-form text to represent named entities, short phrases, and events as their nodes.
Current methods leverage semantic similarities to increase the graph density, but the semantic plausibility of the nodes and their relations are under-explored.
We propose to adopt textual entailment to find implicit entailment relations between CSKG nodes, to effectively densify the subgraph connecting nodes within the same conceptual class.
arXiv Detail & Related papers (2024-02-15T02:27:23Z) - Sheaf Hypergraph Networks [10.785525697855498]
We introduce cellular sheaves for hypergraphs, a mathematical construction that adds extra structure to the conventional hypergraph.
Drawing inspiration from existing Laplacians in the literature, we develop two unique formulations of sheaf hypergraph Laplacians.
We employ these sheaf hypergraph Laplacians to design two categories of models: Sheaf Hypergraph Neural Networks and Sheaf Hypergraph Convolutional Networks.
arXiv Detail & Related papers (2023-09-29T10:25:43Z) - Learning from Heterogeneity: A Dynamic Learning Framework for Hypergraphs [22.64740740462169]
We propose a hypergraph learning framework named LFH that is capable of dynamic hyperedge construction and attentive embedding update.<n>To evaluate the effectiveness of our proposed framework, we conduct comprehensive experiments on several popular datasets.
arXiv Detail & Related papers (2023-07-07T06:26:44Z) - Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A
Relational Anonymous Walk-guided Neural Process Approach [49.00753238429618]
Few-shot inductive link prediction on knowledge graphs aims to predict missing links for unseen entities with few-shot links observed.
Recent inductive methods utilize the sub-graphs around unseen entities to obtain the semantics and predict links inductively.
We propose a novel relational anonymous walk-guided neural process for few-shot inductive link prediction on knowledge graphs, denoted as RawNP.
arXiv Detail & Related papers (2023-06-26T12:02:32Z) - From Hypergraph Energy Functions to Hypergraph Neural Networks [94.88564151540459]
We present an expressive family of parameterized, hypergraph-regularized energy functions.
We then demonstrate how minimizers of these energies effectively serve as node embeddings.
We draw parallels between the proposed bilevel hypergraph optimization, and existing GNN architectures in common use.
arXiv Detail & Related papers (2023-06-16T04:40:59Z) - Equivariant Hypergraph Diffusion Neural Operators [81.32770440890303]
Hypergraph neural networks (HNNs) using neural networks to encode hypergraphs provide a promising way to model higher-order relations in data.
This work proposes a new HNN architecture named ED-HNN, which provably represents any continuous equivariant hypergraph diffusion operators.
We evaluate ED-HNN for node classification on nine real-world hypergraph datasets.
arXiv Detail & Related papers (2022-07-14T06:17:00Z) - Learnable Hypergraph Laplacian for Hypergraph Learning [34.28748027233654]
HyperGraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph structured data.
We propose the first learning-based method tailored for constructing adaptive hypergraph structure, termed HypERgrAph Laplacian aDaptor (HERALD)
HERALD adaptively optimize the adjacency relationship between hypernodes and hyperedges in an end-to-end manner and thus the task-aware hypergraph is learned.
arXiv Detail & Related papers (2021-06-12T02:07:07Z) - Learnable Hypergraph Laplacian for Hypergraph Learning [34.28748027233654]
HyperGraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph structured data.
We propose the first learning-based method tailored for constructing adaptive hypergraph structure, termed HypERgrAph Laplacian aDaptor (HERALD)
HERALD adaptively optimize the adjacency relationship between hypernodes and hyperedges in an end-to-end manner and thus the task-aware hypergraph is learned.
arXiv Detail & Related papers (2021-06-10T12:37:55Z) - HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphs [24.737560790401314]
We present HyperSAGE, a novel hypergraph learning framework that uses a two-level neural message passing strategy to accurately and efficiently propagate information through hypergraphs.
We show that HyperSAGE outperforms state-of-the-art hypergraph learning methods on representative benchmark datasets.
arXiv Detail & Related papers (2020-10-09T13:28:06Z) - Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph
Link Prediction [69.1473775184952]
We introduce a realistic problem of few-shot out-of-graph link prediction.
We tackle this problem with a novel transductive meta-learning framework.
We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction.
arXiv Detail & Related papers (2020-06-11T17:42:46Z) - Generative Adversarial Zero-Shot Relational Learning for Knowledge
Graphs [96.73259297063619]
We consider a novel formulation, zero-shot learning, to free this cumbersome curation.
For newly-added relations, we attempt to learn their semantic features from their text descriptions.
We leverage Generative Adrial Networks (GANs) to establish the connection between text and knowledge graph domain.
arXiv Detail & Related papers (2020-01-08T01:19:08Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.