Workshop. Topological deep Learning: A new direction for artificial intelligence with healthcare applications.

位相幾何学・ディープラーニング: 健康管理に応用される人工知能の新たな方向性

This workshop has been developed as part of a workshop for the 3rd Big Data Machine Learning in Healthcare in Japan@TMDU event that took place in Tokyo in 2023.

Overview of the workshop:

Topological Deep Learning and Geometric Deep Learning (TDL/GDL) are emerging fields at the intersection of mathematics, computer science, and artificial intelligence. This workshop aims to introduce participants to the principles and applications of these two fields in the context of healthcare.

First, an introduction to the fundamental concepts will be made. This approach focuses on extending traditional deep learning techniques to handle different data structures such as graphs, meshes, and point clouds. Participants will learn about graph neural networks, higher-order networks, and other architectures. The second part of the workshop will delve into the potential applications these fields in healthcare. The applications include drug discovery, molecule properties prediction and diagnosis of some diseases. Participants will have the opportunity to engage in hands-on activities through a notebook and interactive discussions.

By the end of the workshop, attendees will be equipped with the knowledge to explore these exciting fields further and apply its techniques to tackle real-world healthcare challenges.

Bringing a laptop will be essential for experimenting with the notebook. While some experience in computer science and/or mathematics is beneficial to understand some concepts, the workshop will be designed to be accessible to a wide audience.

Table of Contents

• Workshop. Topological deep Learning: A new direction for artificial intelligence with healthcare applications.
• 位相幾何学・ディープラーニング: 健康管理に応用される人工知能の新たな方向性
  • Table of Contents
  • Workshop
  • Introduction
  • Author
  • Installation
  • Citation
  • Acknowledgement
  • License

Workshop

Introduction

This workshop consists of a notebook. The goals of this notebook are:

• Briefly present what are Topological Deep Learning (and Geometric Deep Learning) by providing some explanations, definitions, visuals, etc
• Present the potential applications in healthcare and some work that have been done so far in these emerging fields
• Run some code to get some hands-on experience

If you find this workshop interesting, we would appreciate your support by leaving a star ⭐ on this GitHub repository. Feel free to reuse it or some parts for educational/research purpose and don't forget to cite!

Author

Adrien Carrel MSc Advanced Computing at Imperial College London, United Kingdom, MEng in Applied Mathematics (Diplôme d'Ingénieur) at CentraleSupélec, France.

Installation

Download manually the files or clone the repository using, for example, the following command:

bash git clone https://github.com/AdrienC21/workshop_tdl_healthcare.git

Then run the notebook workshop_japan.ipynb. You can run it on Google Colab.

If you don't want all the "solutions" and want some small coding exercises, run instead the notebook workshop_japan_v2.ipynb. You can run it on Google Colab too.

Citation

If you use content from this workshop in your research, course, etc, please consider citing it using the following BibTeX entry:

bibtex Carrel, A. (2023). Workshop. Topological deep Learning: A new direction for artificial intelligence with healthcare applications. (Version 1.0.0) [Computer software]. https://github.com/AdrienC21/workshop_tdl_healthcare

Acknowledgement

Thanks to the organizers of the Datathon Japan 2023 and the participants for providing me with this opportunity. Special thanks to Tolga Birdal, Mustafa Hajij, Nina Miolane and the rest of the authors in the two papers below. Some ideas have also been inspired by the work of Li et al. (see below) and the Hands-on on graph neural network written by Google. I would also like to thank all the authors of the papers that I mentionned in this notebook.

• Papillon et al. : Architectures of Topological Deep Learning: A Survey of Topological Neural Networks (2023)

• Hajij et al. : Topological Deep Learning: Going Beyond Graph Data

• Li et al. : Graph Representation Learning in Biomedicine and Healthcare (2022)

• Adrien Carrel: Combinatorial Complex Score-based Diffusion Modeling through Stochastic Differential Equations (2023)

License

This workshop is licensed under the MIT License. Feel free to use and modify the code as per the terms of the license.