CfP FoDS Special Issue “Recent Advances in Topological Deep Learning”

Call for Papers
Special Issue of Foundations of Data Science
“Recent Advances in Topological Deep Learning”

Description: Data-driven discovery is widely regarded as the fourth paradigm that can fundamentally change scientific research landscape and pave the way for a new industrial revolution. The great success, from AlphaFold to ChatGPT, has demonstrated enormous power of artificial intelligence (AI)-based approaches. However, efficient representations and featurization of complex systems are still one of the central challenges for all the AI-based discoveries. Recently, topological data analysis (TDA) has brought in a new way for data characterization and modelling. Deeply rooted in algebraic topology and computational topology, TDA enables an effective balance between data description and model generalization. TDA-based deep learning models have already shown tremendous power in various applications, such as image processing, drug design, materials design, gene analysis, virus evolution, etc. Topological deep learning has emerged as a new interdisciplinary area between applied topology, data science, and machine learning.

The objective of this special issue is three-fold. First, it aims to showcase recent progress and success in TDA and topological deep learning. Second, it promotes new algorithms, methods, and models in topological deep learning. Third, this special issue is devoted to the 4th conference on “Computational Topology and Application” at the Tsinghua Sanya International Mathematics Forum (TSIMF) in Sanya, China, Dec 18-22, 2023. 


To this end, this special issue of Topological deep learning seeks original papers on the following topics including, but not limited to:
• Topological data analysis and its applications
• Multidimensional persistence, Zig-zag persistence
• Reeb graph, discrete Morse theory, Conley index,
• Path complex, Neighborhood complex, Dowker complex, hypergraph,
• hyperdigraph and their persistent homology and/or Laplacians
• Geometric anomaly detection, differential geometry, discrete exterior calculus
• Spectral graph, spectral simplicial complex, spectral hyper(di)graph
• Topological Laplacians and topological Diracs
• Persistent homology, persistent Laplacian, and other persistent forms
• Cellular Sheaves, periodic cell complex, periodic topology, and local topology
• Dimension reduction (manifold learning, Isomap, Laplacian eigenmaps, diffusion maps, UMAP, MAPPER, hyperbolic geometry, Poincaré embedding, etc)
• Geometric deep learning, graph neural network, simplex complex neural network

Target Dates:
• Manuscript submission Deadline: October 10, 2023 (Will be extended)
• Completion of Peer Reviews: December 10, 2023
• Publication Date: January 30, 2024

Guest Editors:
• Guowei Wei (weig@msu.edu), Michigan State University
• Jie Wu (wujie@bimsa.cn), Beijing Institute of Mathematical Sciences and Applications (BIMSA)
• Duc Nguyen (ducnguyen@uky.edu), University of Kentucky
• Kelin Xia (xiakelin@ntu.edu.sg), Nanyang Technological UniversityMore detailed information can be found https://www.aimsciences.org/FoDS/news/3825

Leave a Reply

Your email address will not be published. Required fields are marked *

 

This site uses Akismet to reduce spam. Learn how your comment data is processed.