ICML 2023 Topological Deep Learning Challenge : Design and Results

1 code implementation • 26 Sep 2023 • Mathilde Papillon, Mustafa Hajij, Helen Jenne, Johan Mathe, Audun Myers, Theodore Papamarkou, Tolga Birdal, Tamal Dey, Tim Doster, Tegan Emerson, Gurusankar Gopalakrishnan, Devendra Govil, Aldo Guzmán-Sáenz, Henry Kvinge, Neal Livesay, Soham Mukherjee, Shreyas N. Samaga, Karthikeyan Natesan Ramamurthy, Maneel Reddy Karri, Paul Rosen, Sophia Sanborn, Robin Walters, Jens Agerberg, Sadrodin Barikbin, Claudio Battiloro, Gleb Bazhenov, Guillermo Bernardez, Aiden Brent, Sergio Escalera, Simone Fiorellino, Dmitrii Gavrilev, Mohammed Hassanin, Paul Häusner, Odin Hoff Gardaa, Abdelwahed Khamis, Manuel Lecha, German Magai, Tatiana Malygina, Rubén Ballester, Kalyan Nadimpalli, Alexander Nikitin, Abraham Rabinowitz, Alessandro Salatiello, Simone Scardapane, Luca Scofano, Suraj Singh, Jens Sjölund, Pavel Snopov, Indro Spinelli, Lev Telyatnikov, Lucia Testa, Maosheng Yang, Yixiao Yue, Olga Zaghen, Ali Zia, Nina Miolane

This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning.

Topological Signal Processing using the Weighted Ordinal Partition Network

no code implementations • 27 Apr 2022 • Audun Myers, Firas A. Khasawneh, Elizabeth Munch

For this task, we turn to the field of topological data analysis (TDA), which encodes information about the shape and structure of data.

Change Point Detection Time Series +2

Effects of Correlated Noise on the Performance of Persistence Based Dynamic State Detection Methods

no code implementations • 31 Aug 2020 • Joshua Tempelman, Audun Myers, Jeffrey Scruggs, Firas Khasawneh

The ability to characterize the state of dynamic systems has been a pertinent task in the time series analysis community.

Time Series Time Series Analysis

Persistent Homology of Complex Networks for Dynamic State Detection

no code implementations • 16 Apr 2019 • Audun Myers, Elizabeth Munch, Firas A. Khasawneh

Specifically, we show how persistent homology, a tool from TDA, can be used to yield a compressed, multi-scale representation of the graph that can distinguish between dynamic states such as periodic and chaotic behavior.

Chaotic Dynamics Computational Geometry Information Theory Information Theory Data Analysis, Statistics and Probability