Explore the concept of learning distances for attributed graphs using optimal transport in this comprehensive webinar presented by Pierre Borgnat from CNRS. Gain insights into this advanced topic as part of the Data sciEnce on GrAphS (DEGAS) Webinar Series, organized in collaboration with the IEEE Signal Processing Society Data Science Initiative. Delve into the intricacies of graph theory and data science, and discover how optimal transport techniques can be applied to measure distances between attributed graphs. Enhance your understanding of this cutting-edge research area and its potential applications in signal processing and data analysis.
Learning Distances for Attributed Graphs with Optimal Transport
IEEE Signal Processing Society via YouTube
Overview
Syllabus
Learning distances for attributed graphs with optimal transport
Taught by
IEEE Signal Processing Society
Related Courses
-
Optimal Transport for Graphs: Definitions and Applications to Graph-Signal Processing
-
Signal Processing on Graphs and Complexes
-
Connecting the Dots - Leveraging GSP to Learn Graphs From Nodal Observations
-
Distributed Stochastic Non-Convex Optimization - Optimal Regimes and Tradeoffs
-
Graph Adjacency Spectral Embeddings - Algorithmic Advances and Applications
-
Data Science on Graphs (DEGAS) Webinar Series - Signal Processing Applications
