This paper investigates the effects of structural and temporal inhomogeneities in decentralised federated learning and shows that they significantly slow down the convergence process.

This paper proposes gspDAG-FL, a secure decentralized federated learning framework that derives consensus from gossip history, improving finality and resilience.

This paper proposes a decentralized collaborative learning paradigm for Tsetlin Machines using consensus-based inference, allowing heterogeneous agents to maintain their own private models and combine…

FedIDM introduces a novel federated learning framework that uses iterative distribution matching to achieve fast and stable convergence and maintain high model utility even when facing a large proport…

The paper proposes a novel decentralized framework that uses blockchain and Multi-task Peer Prediction to incentivize and manage the computationally intensive process of Federated Learning.

The paper addresses secure distributed hypothesis testing, proving impossibility in the standard setting and achieving secure testing for simple and general classes by incorporating a shared secret ke…

This paper introduces the FedSaSync strategy for Semi-Asynchronous Federated Learning in the Flower framework, improving robustness and reducing idle time in heterogeneous environments.

DDP-SA is a novel federated learning framework that combines local differential privacy and secure aggregation to achieve robust, scalable, and highly private model training.

The paper proposes AdaBFL, a multi-layer defensive adaptive aggregation method that enhances Byzantine-robust federated learning by adaptively adjusting defense weights to counter complex poisoning at…

This paper proposes a compression scheme for transmitting sparse local updates in distributed learning systems, and provides a converse based on f-divergence to characterize the communication-accuracy…

This paper introduces a unified threat model and evaluation framework to systematically compare privacy-preserving techniques for distributed learning in IoT systems, highlighting the trade-off betwee…

This review comprehensively analyzes state-of-the-art decentralized trust and security mechanisms, concluding that while these approaches enhance privacy and resilience for IoT edge networks, challeng…

This paper proposes improvements to rotating-leader consensus protocols and their underlying P2P networks in blockchain systems, achieving up to 7.26x peak throughput improvement.

This paper proves the conjecture that Local SGD outperforms Mini-batch SGD under bounded second-order heterogeneity for general convex objectives, improving the convergence guarantee and lower bounds.

This paper proposes and evaluates the integration of Federated Learning and blockchain technology over cloud-edge infrastructure to enhance data privacy and security for decentralized AI applications.

The paper proposes Byz-Clip21-SGD2M, a novel algorithm that achieves high-probability convergence guarantees for Federated Learning by integrating robust aggregation, double momentum, and clipping, re…

This paper investigates how network perturbations can alter the asymptotic agreement trajectory in distributed coordination systems, proving fragility in standard cooperative output regulation schemes…