Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs

Zantedeschi, Valentina; Bellet, Aurelien; Tommasi, Marc

Document type :

Communication dans un congrès avec actes

Title :

Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs

Author(s) :

Zantedeschi, Valentina [Auteur]
Bellet, Aurelien [Auteur]

Machine Learning in Information Networks [MAGNET]
Tommasi, Marc [Auteur]

Machine Learning in Information Networks [MAGNET]

Conference title :

AISTATS 2020 - The 23rd International Conference on Artificial Intelligence and Statistics

City :

Palerme / Virtual

Country :

Italie

Start date of the conference :

2020-08-26

HAL domain(s) :

Informatique [cs]/Apprentissage [cs.LG]
Statistiques [stat]/Machine Learning [stat.ML]

English abstract : [en]

We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator. We propose to train ...
Show more >We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator. We propose to train personalized models that leverage a collaboration graph describing the relationships between user personal tasks, which we learn jointly with the models. Our fully decentralized optimization procedure alternates between training nonlinear models given the graph in a greedy boosting manner, and updating the collaboration graph (with controlled sparsity) given the models. Throughout the process, users exchange messages only with a small number of peers (their direct neighbors when updating the models, and a few random users when updating the graph), ensuring that the procedure naturally scales with the number of users. Overall, our approach is communication-efficient and avoids exchanging personal data. We provide an extensive analysis of the convergence rate, memory and communication complexity of our approach, and demonstrate its benefits compared to competing techniques on synthetic and real datasets.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

Apprentissage automatique décentralisé et personnalisé sous contraintes
Apprendre avec des vues interactionnelles

Collections :