FedFNN: Faster Training Convergence Through Update Predictions in Federated Recommender Systems

TL;DR

FedFNN is a novel federated learning algorithm that significantly accelerates training convergence in recommender systems by predicting updates for unsampled users, achieving faster training without sacrificing accuracy.

Contribution

Introduces FedFNN, a method that predicts weight updates for unsampled users to speed up federated training in recommender systems.

Findings

FedFNN is 5x faster than existing methods.

Maintains or improves accuracy during faster training.

Performs consistently across different client cluster configurations.

Abstract

Federated Learning (FL) has emerged as a key approach for distributed machine learning, enhancing online personalization while ensuring user data privacy. Instead of sending private data to a central server as in traditional approaches, FL decentralizes computations: devices train locally and share updates with a global server. A primary challenge in this setting is achieving fast and accurate model training - vital for recommendation systems where delays can compromise user engagement. This paper introduces FedFNN, an algorithm that accelerates decentralized model training. In FL, only a subset of users are involved in each training epoch. FedFNN employs supervised learning to predict weight updates from unsampled users, using updates from the sampled set. Our evaluations, using real and synthetic data, show: 1. FedFNN achieves training speeds 5x faster than leading methods, maintaining or improving accuracy; 2. the algorithm's performance is consistent regardless of client cluster variations; 3. FedFNN outperforms other methods in scenarios with limited client availability, converging more quickly.