no code implementations • 15 Apr 2024 • Sayan Biswas, Mathieu Even, Anne-Marie Kermarrec, Laurent Massoulie, Rafael Pires, Rishi Sharma, Martijn de Vos
We theoretically prove the convergence of Shatter and provide a formal analysis demonstrating how Shatter reduces the efficacy of attacks compared to when exchanging full models between participating nodes.
no code implementations • 18 Mar 2024 • Sayan Biswas, Davide Frey, Romaric Gaudel, Anne-Marie Kermarrec, Dimitri Lerévérend, Rafael Pires, Rishi Sharma, François Taïani
This paper introduces ZIP-DL, a novel privacy-aware decentralized learning (DL) algorithm that relies on adding correlated noise to each model update during the model training process.
1 code implementation • NeurIPS 2023 • Martijn de Vos, Sadegh Farhadkhani, Rachid Guerraoui, Anne-Marie Kermarrec, Rafael Pires, Rishi Sharma
We present Epidemic Learning (EL), a simple yet powerful decentralized learning (DL) algorithm that leverages changing communication topologies to achieve faster model convergence compared to conventional DL approaches.
1 code implementation • 7 Jun 2023 • Akash Dhasade, Anne-Marie Kermarrec, Rafael Pires, Rishi Sharma, Milos Vujasinovic, Jeffrey Wigger
Decentralized learning (DL) systems have been gaining popularity because they avoid raw data sharing by communicating only model parameters, hence preserving data confidentiality.
1 code implementation • 17 Apr 2023 • Akash Dhasade, Anne-Marie Kermarrec, Rafael Pires, Rishi Sharma, Milos Vujasinovic
Decentralized learning (DL) has gained prominence for its potential benefits in terms of scalability, privacy, and fault tolerance.
1 code implementation • 23 Feb 2022 • Akash Dhasade, Nevena Dresevic, Anne-Marie Kermarrec, Rafael Pires
We analyze the impact of raw data sharing in both deep neural network (DNN) and matrix factorization (MF) recommenders and showcase the benefits of trusted environments in a full-fledged implementation of REX.
no code implementations • 21 Oct 2021 • Mohamed Yassine Boukhari, Akash Dhasade, Anne-Marie Kermarrec, Rafael Pires, Othmane Safsafi, Rishi Sharma
GeL enables constrained edge devices to perform additional learning through guessed updates on top of gradient-based steps.