Hypergraph Foundation Model
This addresses the problem of modeling complex high-order relationships in domains like protein interactions and social networks for researchers and practitioners in graph machine learning, representing a novel method rather than incremental progress.
The paper tackles the challenge of developing foundation models for hypergraphs by introducing Hyper-FM, which outperforms baseline methods by approximately 13.3% on 10 curated datasets and proposes the first scaling law showing domain diversity enhances performance more than increasing vertex/hyperedge counts.
Hypergraph neural networks (HGNNs) effectively model complex high-order relationships in domains like protein interactions and social networks by connecting multiple vertices through hyperedges, enhancing modeling capabilities, and reducing information loss. Developing foundation models for hypergraphs is challenging due to their distinct data, which includes both vertex features and intricate structural information. We present Hyper-FM, a Hypergraph Foundation Model for multi-domain knowledge extraction, featuring Hierarchical High-Order Neighbor Guided Vertex Knowledge Embedding for vertex feature representation and Hierarchical Multi-Hypergraph Guided Structural Knowledge Extraction for structural information. Additionally, we curate 10 text-attributed hypergraph datasets to advance research between HGNNs and LLMs. Experiments on these datasets show that Hyper-FM outperforms baseline methods by approximately 13.3\%, validating our approach. Furthermore, we propose the first scaling law for hypergraph foundation models, demonstrating that increasing domain diversity significantly enhances performance, unlike merely augmenting vertex and hyperedge counts. This underscores the critical role of domain diversity in scaling hypergraph models.