Français
Optimal transport for graphs: definitions, applications to graph-signal processing
Multi angle
Authors : Courty, Nicolas (Author of the conference)
CIRM (Publisher )
68Q32 - Computational learning theory
68T05 - Learning and adaptive systems
Additional resources :
https://www.cirm-math.fr/RepOrga/2588/Slides/courty.pdf
CIRM (Publisher )
Loading the player...
|
Abstract :
In this talk I will discuss how a variant of the classical optimal transport problem, known as the Gromov-Wasserstein distance, can help in designing learning tasks over graphs, and allow to transpose classical signal processing or data analysis tools such as dictionary learning or online change detection, for learning over those types of structured objects. Both theoretical and practical aspects will be discussed.
Keywords : transport optimal; graphs; Gromov-Wasserstein
MSC Codes : Keywords : transport optimal; graphs; Gromov-Wasserstein
68Q32 - Computational learning theory
68T05 - Learning and adaptive systems
Additional resources :
https://www.cirm-math.fr/RepOrga/2588/Slides/courty.pdf
|
Information on the Video
Film maker : Hennenfent, GuillaumeLanguage : English Available date : 05/12/2022 Conference Date : 10/11/2022 Subseries : Research talks arXiv category : Machine Learning Mathematical Area(s) : Computer Science Format : MP4 (.mp4) - HD Video Time : 00:54:45 Targeted Audience : Researchers ; Graduate Students ; Doctoral Students, Post-Doctoral Students Download : https://videos.cirm-math.fr/2022-11-10_Courty.mp4 
|
Information on the Event
Event Title : Machine Learning and Signal Processing on Graphs / Apprentissage automatique et traitement du signal sur graphesEvent Organizers : Keriven, Nicolas ; Loukas, Andreas ; Pustelnik, Nelly ; Tremblay, Nicolas ; Vaiter, Samuel Dates : 07/11/2022 - 11/11/2022 Event Year : 2022 Event URL : https://conferences.cirm-math.fr/2588.html
Citation Data
DOI : 10.24350/CIRM.V.19981603Cite this video as: Courty, Nicolas (2022). Optimal transport for graphs: definitions, applications to graph-signal processing. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19981603 URI : http://dx.doi.org/10.24350/CIRM.V.19981603 |
See Also
- [Multi angle] Clustering with tangles / Author of the conference von Luxburg, Ulrike ; Author of the conference Klepper, Solveig.
- [Multi angle] Subgraph-based networks for expressive, efficient, and domain-independent graph learning / Author of the conference Maron, Haggai.
- [Multi angle] Statistical comparisons of spatio-temporal networks / Author of the conference Achard, Sophie.
Bibliography
Imagette Video
