首个超图基础模型，提升多领域知识提取能力。
Hypergraph Foundation Model
- 分层高阶邻居引导嵌入，捕捉顶点特征
- 跨超图结构信息提取，性能比基线高13.4%
- 强调领域多样性对模型扩展的关键作用
超图神经网络（HGNNs）通过超边连接多个顶点，有效建模蛋白质相互作用、社交网络等领域的复杂高阶关系，提升建模能力并减少信息损失。由于超图数据包含顶点特征与复杂结构信息，构建其基础模型面临挑战。本文提出Hyper-FM，一种用于多领域知识提取的超图基础模型，包含分层高阶邻居引导的顶点知识嵌入与分层多超图引导的结构知识提取机制。同时，我们构建了11个带文本属性的超图数据集，推动HGNN与大语言模型研究融合。实验表明，Hyper-FM在这些数据集上性能优于基线方法约13.4%。此外，我们首次提出超图基础模型的缩放定律，证明增加领域多样性显著提升性能，而单纯增加顶点与超边数量效果有限，凸显领域多样性在模型扩展中的关键作用。
原文摘要 · Abstract (English)
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 11 text-attributed hypergraph datasets to advance research between HGNNs and LLMs. Experiments on these datasets show that Hyper-FM outperforms baseline methods by approximately 13.4%, 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。