Simplicial complexes can be viewed as high dimensional generalizations of graphs that explicitly encode multi-way ordered relations between vertices at different resolutions, all at once. This concept is central towards detection of higher dimensional topological features of data, features to which graphs, encoding only pairwise relationships, remain oblivious. While attempts have been made to extend Graph Neural Networks (GNNs) to a simplicial complex setting, the methods do not inherently exploit, or reason about, the underlying topological structure of the network. We propose a graph convolutional model for learning functions parametrized by the $k$-homological features of simplicial complexes. By spectrally manipulating their combinatorial $k$-dimensional Hodge Laplacians, the proposed model enables learning topological features of the underlying simplicial complexes, specifically, the distance of each $k$-simplex from the nearest "optimal" $k$-th homology generator, effectively providing an alternative to homology localization.
翻译:简单复合物可被视为对图表的高度概括化,这些图形明确将不同分辨率的脊椎之间的多向排列关系编码为多向关系,这些都同时存在。这个概念对于发现数据中较高维度的地形特征至关重要,因为图形的特征(仅对对称关系进行编码)仍然不为人知。虽然有人试图将图形神经网络(GNN)扩展为简单复杂环境,但方法本身并不利用或解释网络的基本地形结构。我们提出了一个图形共变模型,用于学习由简易复杂物的美元-同源物学特征相匹配的功能。通过光谱管理其组合式的元-美元-维维-Hodge Laplacecians,拟议的模型使得能够学习基础简易复合体的地形特征,特别是每个美元-简单分解器与最近的“最佳”美元-同质学发电机的距离,有效地提供了同质学本地化的替代方法。