Position: topological deep learning is the new frontier for relational learning
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
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.
Date Issued
2024
Date Acceptance
2024-07-21
Citation
Proceedings of Machine Learning Research, 2024, 235, pp.39529-39555
ISSN
2640-3498
Publisher
Proceedings of Machine Learning Research
Start Page
39529
End Page
39555
Journal / Book Title
Proceedings of Machine Learning Research
Volume
235
Copyright Statement
Copyright 2024 by
the author(s).
This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
the author(s).
This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Identifier
https://proceedings.mlr.press/v235/papamarkou24a.html
Source
41st International Conference on Machine Learning
Publication Status
Published
Start Date
2024-07-21
Finish Date
2024-07-27
Coverage Spatial
Vienna, Austria
Date Publish Online
2024-07-21