Topological Deep Learning: Going Beyond Graph Data | Mustafa Hajij

Try datamol.io - the open source toolkit that simplifies molecular processing and featurization workflows for machine learning scientists working in drug discovery: https://datamol.io/

Never miss another LoGG Talk, add the schedule to your calendar: https://m2d2.io/talks/m2d2/about/

Join the Learning on Graphs and Geometry Reading Group on Slack: https://join.slack.com/t/logag/shared...

Abstract: Topological deep learning is a rapidly growing field that pertains to the development of deep learning models for data supported on topological domains such as simplicial complexes, cell complexes, and hypergraphs, which generalize many domains encountered in scientific computations. In this paper, we present a unifying deep learning framework built upon a richer data structure that includes widely adopted topological domains.

Speaker: Mustafa Hajij - http://www.mustafahajij.com/

Twitter Hannes:   / hannesstaerk  
Twitter Dominique:   / dom_beaini  
Twitter datamol.io:   / datamol_io  

~

Chapters

00:00 - Intro
09:09 - Efficient Message Passing Over Long Range
12:31 - Neighborhood Functions
16:11 - Bridging the Gap Between Higher-Order Domains
23:49 - CC-Embeddings: Enriching Domains
26:08 - Continous vs. Discrete Neighborhoods
34:58 - Intro to Combinatorial Complex Neural Networks
41:30 - CC-Pooling and CC-Unpooling
49:50 - Mesh Segmentation: Results
54:02 - Q+A