Position: Topological Deep Learning is the New Frontier for Relational Learning
University of Manchester · Imperial College London · University of Oxford · Stanford University · University at Albany, SUNY · Tsinghua University, Tsinghua University · University of San Francisco · University of Salzburg · University of Cambridge · University of Roma "La Sapienza" · University of Tennessee Knoxville · University of California, Santa Barbara · University of Hawaii at Manoa · IBM Research · Helmholtz Munich & Technical University of Munich · Sapienza University of Rome · RWTH Aachen University · Google DeepMind / University of Cambridge · University of Utah · UC San Diego · Michigan State University
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation learning and geometric deep learning by incorporating topological concepts, and can thus provide a natural choice for various machine learning settings. To this end, this paper discusses open problems in TDL, ranging from practical benefits to theoretical foundations. For each problem, it outlines potential solutions and future research opportunities. At the same time, this paper serves as an invitation to the scientific community to actively participate in TDL research to unlock the potential of this emerging field.