<ul data-eligibleForWebStory="false"><li>Researchers have proposed the use of consensus-based protocols to determine a subset of clients with the most useful model weights in federated learning to reduce data transfer costs.</li><li>A new fluid democracy protocol named viscous-retained democracy has been introduced, offering better performance than traditional methods like 1p1v (FedAvg) without allowing influence accumulation.</li><li>The study also addresses weaknesses of fluid democracy protocols from an adversarial perspective, highlighting vulnerabilities related to topology and number of adversaries. A new algorithm, FedVRD, aims to limit adversarial impact while optimizing cost through delegation topology.</li></ul>

Fluid Democracy in Federated Data Aggregation

Discover more