FLeet: Online Federated Learning via Staleness Awareness and Performance Prediction

no code implementations • 12 Jun 2020 • Georgios Damaskinos, Rachid Guerraoui, Anne-Marie Kermarrec, Vlad Nitu, Rhicheek Patra, Francois Taiani

Federated Learning (FL) is very appealing for its privacy benefits: essentially, a global model is trained with updates computed on mobile devices while keeping the data of users local.

Federated Learning

Asynchronous Byzantine Machine Learning (the case of SGD)

1 code implementation • ICML 2018 • Georgios Damaskinos, El Mahdi El Mhamdi, Rachid Guerraoui, Rhicheek Patra, Mahsa Taziki

The dampening component bounds the convergence rate by adjusting to stale information through a generic gradient weighting scheme.

BIG-bench Machine Learning

Sequences, Items And Latent Links: Recommendation With Consumed Item Packs

no code implementations • 16 Nov 2017 • Rachid Guerraoui, Erwan Le Merrer, Rhicheek Patra, Jean-Ronan Vigouroux

In this paper, we introduce the notion of consumed item pack (CIP) which enables to link users (or items) based on their implicit analogous consumption behavior.

Collaborative Filtering

BoostJet: Towards Combining Statistical Aggregates with Neural Embeddings for Recommendations

no code implementations • 15 Nov 2017 • Rhicheek Patra, Egor Samosvat, Michael Roizner, Andrei Mishchenko

These applications rely on recommenders for generating advertisements for various offers or providing content recommendations.