paper-with-me

Papers

Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs

2019-01-24 · Valentina Zantedeschi, Aurélien Bellet, Marc Tommasi

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.

📄 PDF Abstract BibTeX arXiv:1901.08460

Code (1)

vzantedeschi/Dada 공식 구현

Similar Papers 제목 키워드 기반

Decentralized Directed Collaboration for Personalized Federated Learning

2024-05-28 · CVPR 2024 1 · Yingqi Liu, Yifan Shi, Qinglun Li, Baoyuan Wu 외

Personalized Federated Learning (PFL) is proposed to find the greatest personalized models for each client. To avoid the central failure and communication bottleneck in the server-based FL, we concentrate on the Decentra…

Federated LearningPersonalized Federated Learning

Decentralized Personalized Federated Learning

2024-06-10 · Salma Kharrat, Marco Canini, Samuel Horvath

This work tackles the challenges of data heterogeneity and communication limitations in decentralized federated learning. We focus on creating a collaboration graph that guides each client in selecting suitable collabora…

Federated LearningPersonalized Federated Learning

Communication-Constrained Private Decentralized Online Personalized Mean Estimation

2025-11-02 · Yauhen Yakimenka, Hsuan-Yin Lin, Eirik Rosnes, Jörg Kliewer arxiv

We consider the problem of communication-constrained collaborative personalized mean estimation under a privacy constraint in an environment of several agents continuously receiving data according to arbitrary unknown ag…

MAPL: Model Agnostic Peer-to-peer Learning

2024-03-28 · Sayak Mukherjee, Andrea Simonetto, Hadi Jamali-Rad

Effective collaboration among heterogeneous clients in a decentralized setting is a rather unexplored avenue in the literature. To structurally address this, we introduce Model Agnostic Peer-to-peer Learning (coined as M…

Graph LearningmodelPrivacy Preserving

Decentralized Collaborative Learning of Personalized Models over Networks

2016-10-17 · Paul Vanhaesebrouck, Aurélien Bellet, Marc Tommasi

We consider a set of learning agents in a collaborative peer-to-peer network, where each agent learns a personalized model according to its own learning objective. The question addressed in this paper is: how can agents …