多粒度自适应超图表示学习：基于粒球的方法
Multi-granularity Adaptive Hypergraph Representation Learning via Granular-ball
浏览论文内容
中文总结 AI 辅助
针对现有超图方法忽视拓扑多样性与多粒度的问题，提出MGHRL框架，利用粒球自适应分裂生成多粒度超边，并通过多子网络与层次可逆连接整合特征，在基准数据集上显著优于基线。
中文摘要 AI 辅助
超图表示学习旨在通过构建同时连接多个节点的超边来捕获图中的高阶信息。这些超边适应图的拓扑特征，有助于在多个粒度上提取高阶关系。以往的大多数工作依赖预定义规则来生成超边，忽视了图拓扑结构的多样性以及超边的多粒度特性。因此，这限制了它们有效且自适应地发现高阶关系以及高效处理复杂结构信息的能力。为了解决这一局限，我们提出了一种名为多粒度超图表示学习（MGHRL）的新框架。MGHRL引入了一种自适应粒度超图生成策略，通过粒球的自适应分裂在多个粒度级别生成超边，从而基于图的拓扑结构有效捕获高阶关系。此外，我们提出了一种包含多个子网络的多粒度超图网络，从不同粒度的超边中提取特征，并通过层次可逆连接进行整合。实验结果表明，MGHRL在基准数据集上显著优于基线模型。
英文摘要
Hypergraph representation learning aims to capture high-order information in graphs by constructing hyperedges that simultaneously connect multiple nodes. These hyperedges adapt to the graph's topological features, facilitating the extraction of high-order relationships at multiple granularities. Most prior work relies on predefined definitions to generate hyperedges, overlooking the diversity in graph topological structures and the multi-granularity characteristics of hyperedges. As a result, this limits their ability to effectively and adaptively discover high-order relationships and efficiently process complex structural information. To address this limitation, we propose a novel framework called \underline{M}ulti-\underline{G}ranularity \underline{H}ypergraph \underline{R}epresentation \underline{L}earning (MGHRL). MGHRL introduces an Adaptive Granular Hypergraph Generation strategy, which generates hyperedges at multiple levels of granularity through the adaptive splitting of granular-ball, effectively capturing high-order relationships based on the graph's topological structure. Additionally, we propose a Multi-Granularity Hypergraph Network with multiple sub-networks, capturing features from hyperedges at different granularities and integrating them via hierarchical reversible connections. Experimental results show that MGHRL significantly outperforms baseline models on benchmark datasets.
