Fully Decentralized Joint Learning of ...
Document type :
Rapport de recherche: Autre communication scientifique (congrès sans actes - poster - séminaire...)
Title :
Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs
Author(s) :
Zantedeschi, Valentina [Auteur]
Laboratoire Hubert Curien [LabHC]
Bellet, Aurelien [Auteur]
Machine Learning in Information Networks [MAGNET]
Tommasi, Marc [Auteur]
Machine Learning in Information Networks [MAGNET]
Laboratoire Hubert Curien [LabHC]
Bellet, Aurelien [Auteur]
Machine Learning in Information Networks [MAGNET]
Tommasi, Marc [Auteur]
Machine Learning in Information Networks [MAGNET]
Institution :
Inria
Publication date :
2019
HAL domain(s) :
Informatique [cs]/Apprentissage [cs.LG]
Statistiques [stat]/Machine Learning [stat.ML]
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 the users' 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 in the graph and a few random users), ensuring that the procedure naturally scales to large numbers of users. We analyze 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 >
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 the users' 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 in the graph and a few random users), ensuring that the procedure naturally scales to large numbers of users. We analyze 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
ANR Project :
Collections :
Source :
Files
- https://hal.inria.fr/hal-02166433/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02166433/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02166433/document
- Open access
- Access the document
- https://hal.inria.fr/hal-02166433/document
- Open access
- Access the document
- document
- Open access
- Access the document
- 1901.08460.pdf
- Open access
- Access the document