… federated learning as a basis, we explore and present refinements in terms of boosted
communication efficiency … side, a known bottleneck for federated learning, due to various reasons …

… • We formally define the data erasure problem in federated learning and propose an
efficient and effective retraining algorithm. Our proposed algorithm is model agnostic and can …

… , and then develop an efficient path-following algorithm for its solution based on the inner
approximation (IA) framework [30]. Numerical results in realistic federated settings are provided …

… Federated learning (FL) emerges as a promising solution aiming to protect user privacy by
enabling model training on a large corpus of decentralized data. The recent studies indicate …

Federated learning (FL) has demonstrated tremendous success in various mission-critical
large-scale scenarios. However, such promising distributed learning paradigm is still …

… Abstract Federated learning (FL) ameliorates privacy concerns in settings where a central
server coordinates learning from data distributed across many clients. The clients train locally …

… We propose ChainsFL, a federated learning framework driven by the two-layer blockchain.
Then, we design a Raft-based blockchain sharding architecture to improve scalability and a …

… 3.1 Decentralized Federated Learning We consider a federated learning system consisting
… with a large number of AIoT devices for federated learning with 6G. These communication …

… Federated learning (FL) has been a popular method to achieve distributed machine learning
… We believe Hermes represents a significant step towards the realization of efficient FL …

… in federated learning and we leverage the interplay between statistical accuracy and system
heterogeneity to design a straggler-resilient federated learning … zi j are iid realizations of a …