手法を比較

	トポロジカル深層学習	永続的ホモロジー
分野	位相幾何学	位相幾何学
系統	Machine learning	Machine learning
提唱年	2023	2002
提唱者	Topological deep learning literature	Edelsbrunner, Letscher & Zomorodian
種類	Higher-order message-passing framework	Topological feature extraction algorithm
原典	Hajij, M., et al. (2023). Topological deep learning: Going beyond graph data. arXiv preprint.	Edelsbrunner, H., Letscher, D., & Zomorodian, A. (2002). Topological persistence and simplification. Discrete & Computational Geometry, 28(4), 511–533.
別名	TDL, Topological Neural Networks, Higher-Order Deep Learning, Topolojik Derin Öğrenme	Topological Persistence, Persistence Barcodes, Persistent Betti Numbers, Kalıcı Homoloji
関連	3	2
概要	Topological Deep Learning (TDL) is a framework that extends deep learning beyond graphs to higher-order topological domains such as simplicial complexes, cell complexes, and hypergraphs. Formalized by Hajij et al. (2023), TDL provides a unified mathematical language for defining message-passing schemes across cells of different ranks, enabling neural networks to model multi-way interactions that pairwise graph edges cannot capture. It is relevant to researchers working with relational, geometric, or biological data exhibiting group-level dependencies.	Persistent homology is a method in topological data analysis that quantifies the multi-scale topological structure of data by tracking connected components, loops, and voids as a scale parameter varies. Introduced by Edelsbrunner, Letscher, and Zomorodian in 2002, it encodes topological features through their birth and death scales, producing persistence diagrams or barcodes that serve as compact, coordinate-free descriptors of shape. The approach is robust to noise and provides a mathematically rigorous bridge between discrete data and algebraic topology.