One of the main challenges of Topological Data Analysis (TDA) is to extract features from persistent diagrams directly usable by machine learning algorithms. Indeed, persistence diagrams are intrinsically (multi-)sets of points in $\mathbb{R}^2$ and cannot be seen in a straightforward manner as vectors. In this article, we introduce $\texttt{Persformer}$, the first Transformer neural network architecture that accepts persistence diagrams as input. The $\texttt{Persformer}$ architecture significantly outperforms previous topological neural network architectures on classical synthetic and graph benchmark datasets. Moreover, it satisfies a universal approximation theorem. This allows us to introduce the first interpretability method for topological machine learning, which we explore in two examples.
Attending to Topological Spaces: The Cellular Transformer
Universitat de Barcelona(巴塞罗那大学);Universidad de Salamanca(萨拉曼卡大学);University of California Santa Barbara(加州大学圣巴巴拉分校);Harvard University(哈佛大学);Imperial College London(伦敦帝国学院);University San Francisco(旧金山大学)
Interaction Topological Transformer for Multiscale Learning in Porous Materials
Department of Mathematics, Michigan State University(数学系,密歇根州立大学);Physical Sciences Division, Pacific Northwest National Laboratory(物理科学部,太平洋西北国家实验室);Department of Electrical and Computer Engineering, Michigan State University(电气与计算机工程系,密歇根州立大学);Department of Biochemistry and Molecular Biology, Michigan State University(生物化学与分子生物学系,密歇根州立大学)
Learning Spatio-Temporal Dynamics for Trajectory Recovery via Time-Aware Transformer
School of Computer Science, Fudan University(复旦大学计算机科学学院);Shanghai Key Laboratory of Data Science, Fudan University(复旦大学数据科学重点实验室);Shanghai Institute of Intelligent Electronics & Systems(上海智能电子与系统研究所);School of Computing and Information Systems, Singapore Management University(新加坡国立大学计算与信息系统学院)
Supercharging Graph Transformers with Advective Diffusion
Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard(埃里克和wendy Schmidt中心,MIT和哈佛大学Broad研究所);Toyota Technological Institute at Chicago(芝加哥丰田技术研究所);Shanghai Jiao Tong University(上海交通大学);University of Oxford(牛津大学)
Predicting Many Crystal Properties via an Adaptive Transformer-based Framework
Fudan University(复旦大学);Shanghai Research Center for Quantum Sciences(上海量子科学研究中心);Institute for Nanoelectronic Devices and Quantum Computing, Zhangjiang Fudan International Innovation Center, Fudan University(复旦大学张江国际创新中心纳米电子器件与量子计算研究所);Hefei National Laboratory(合肥国家实验室)
Skoltech(斯科尔科沃科学技术研究院);CNRS(法国国家科学研究中心);Université Paris Cité(巴黎西岱大学);Artificial Intelligence Research Institute (AIRI)(人工智能研究院(AIRI));St. Petersburg Department of the Steklov Institute of Mathematics(斯捷克洛夫数学研究所圣彼得堡分所)
$p$-adic Bi-Filtrations for Topological Machine Learning on Genomic Sequences
Department of CS & IS, BITS Pilani, K K Birla Goa Campus(计算机科学与信息系统系,比斯潘大学,KK Birla Goa校区);Department of Mathematics, BITS Pilani, K K Birla Goa Campus(数学系,比斯潘大学,KK Birla Goa校区)
Current Topological and Machine Learning Applications for Bias Detection in Text
Staticlysm LLC(斯塔蒂克莱斯姆有限责任公司);Mayo Clinic(梅奥诊所);West Virginia University(西弗吉尼亚大学);Stanford University(斯坦福大学);Harvard University(哈佛大学);University of Dubai(迪拜大学)
Trương Minh Huy Independent Researcher(Trương Minh Huy 独立研究者);Instituto de Matemática, Estatística e Computação Científica University of Campinas (UNICAMP), Brazil(巴西坎皮纳斯大学数学、统计与科学计算研究所)