Fluid Democracy in Federated Data Aggregation

TL;DR

This paper introduces a fluid democracy approach to federated learning that reduces unnecessary data transfer by selecting useful clients, proposes a new protocol that outperforms existing ones, and addresses adversarial vulnerabilities with a dynamic algorithm.

Contribution

It presents a novel fluid democracy protocol for federated learning, improving efficiency and robustness against adversaries compared to traditional methods.

Findings

Viscous-retained democracy outperforms 1p1v in simulations.

The proposed algorithm FedVRD limits adversarial influence effectively.

Fluid democracy protocols can reduce data transfer costs in federated learning.

Abstract

Federated learning (FL) mechanisms typically require each client to transfer their weights to a central server, irrespective of how useful they are. In order to avoid wasteful data transfer costs from clients to the central server, we propose the use of consensus based protocols to identify a subset of clients with most useful model weights at each data transfer step. First, we explore the application of existing fluid democracy protocols to FL from a performance standpoint, comparing them with traditional one-person-one-vote (also known as 1p1v or FedAvg). We propose a new fluid democracy protocol named viscous-retained democracy that always does better than 1p1v under the same assumptions as existing fluid democracy protocols while also not allowing for influence accumulation. Secondly, we identify weaknesses of fluid democracy protocols from an adversarial lens in terms of their dependence on topology and/ or number of adversaries required to negatively impact the global model weights. To this effect, we propose an algorithm (FedVRD) that dynamically limits the effect of adversaries while minimizing cost by leveraging the delegation topology.