超图基础模型
Hypergraph Foundation Model
AI总结：
Hyper-FM是一种多领域知识提取的超图基础模型，通过层次化高阶邻居引导的顶点知识嵌入和结构知识提取，提升超图建模能力，并提出超图基础模型的扩展定律。
摘要：
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和社会网络等领域的复杂高阶关系，从而增强建模能力并减少信息损失。开发超图基础模型具有挑战性，因为其数据包含顶点特征和复杂的结构信息。我们提出了Hyper-FM，一种多领域知识提取的超图基础模型，其包含层次化高阶邻居引导的顶点知识嵌入用于顶点特征表示，以及层次化多超图引导的结构知识提取用于结构信息。此外，我们整理了11个具有文本属性的超图数据集，以推动HGNNs与LLMs之间的研究。在这些数据集上的实验表明，Hyper-FM在基准方法上表现优异，提升了约13.4%，验证了我们的方法。此外，我们提出了超图基础模型的第一个扩展定律，表明增加领域多样性显著提升性能，与单纯增加顶点和超边数量不同。这突显了领域多样性在扩展超图模型中的关键作用。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
