ﻻ يوجد ملخص باللغة العربية
Federated learning is promising for its ability to collaboratively train models with multiple clients without accessing their data, but vulnerable when clients data distributions diverge from each other. This divergence further leads to a dilemma: Should we prioritize the learned models generic performance (for future use at the server) or its personalized performance (for each client)? These two, seemingly competing goals have divided the community to focus on one or the other, yet in this paper we show that it is possible to approach both at the same time. Concretely, we propose a novel federated learning framework that explicitly decouples a models dual duties with two prediction tasks. On the one hand, we introduce a family of losses that are robust to non-identical class distributions, enabling clients to train a generic predictor with a consistent objective across them. On the other hand, we formulate the personalized predictor as a lightweight adaptive module that is learned to minimize each clients empirical risk on top of the generic predictor. With this two-loss, two-predictor framework which we name Federated Robust Decoupling Fed-RoD, the learned model can simultaneously achieve state-of-the-art generic and personalized performance, essentially bridging the two tasks.
As artificial intelligence (AI)-empowered applications become widespread, there is growing awareness and concern for user privacy and data confidentiality. This has contributed to the popularity of federated learning (FL). FL applications often face
As data is generated and stored almost everywhere, learning a model from a data-decentralized setting is a task of interest for many AI-driven service providers. Although federated learning is settled down as the main solution in such situations, the
The lottery ticket hypothesis (LTH) claims that a deep neural network (i.e., ground network) contains a number of subnetworks (i.e., winning tickets), each of which exhibiting identically accurate inference capability as that of the ground network. F
The success of machine learning applications often needs a large quantity of data. Recently, federated learning (FL) is attracting increasing attention due to the demand for data privacy and security, especially in the medical field. However, the per
Federated learning (FL) is an emerging distributed machine learning paradigm that avoids data sharing among training nodes so as to protect data privacy. Under coordination of the FL server, each client conducts model training using its own computing