Typical federated learning (FL) problem formulation requires learning a single model
suitable for all parties while prohibiting parties from sharing their data with the aggregator …

We present a class of methods for robust, personalized federated learning, called Fed+, that
unifies many federated learning algorithms. The principal advantage of this class of methods …

Fed+ is a unified family of methods designed to better accommodate the real-world
characteristics found in federated learning training, such as the lack of IID data across …

Personalized Federated Learning (PFL) is a commonly used framework that allows clients to
collaboratively train their personalized models. PFL is particularly useful for handling …

Personalized federated learning (pFL) has gained significant attention as a promising
approach to address the challenge of data heterogeneity. In this paper, we address a …

A widely recognized difficulty in federated learning arises from the statistical heterogeneity
among clients: local datasets often come from different but not entirely unrelated …

We present a partially personalized formulation of Federated Learning (FL) that strikes a
balance between the flexibility of personalization and cooperativeness of global training. In …

Federated learning is a distributed machine learning approach in which a single server and
multiple clients collaboratively build machine learning models without sharing datasets on …

This chapter explores incentive schemes that encourage clients to participate in federated
learning (FL) and contribute more valuable data. Such schemes are important to enable …

Federated learning (FL) refers to the paradigm of learning models over a collaborative
research network involving multiple clients without sacrificing privacy. Recently, there have …