Papaya: Federated Learning, but Fully Decentralized

TL;DR

This paper proposes a fully decentralized peer-to-peer federated learning system that eliminates the need for a central server, reducing bandwidth use and privacy risks by using a learned trust matrix for parameter sharing.

Contribution

It introduces a novel decentralized federated learning approach with a trust-based peer-to-peer parameter sharing mechanism, moving beyond traditional server-based systems.

Findings

Prototype implementation of peer-to-peer learning system

Successful experiments with virtual nodes on a single machine

Proof of concept for decentralized model sharing

Abstract

Federated Learning systems use a centralized server to aggregate model updates. This is a bandwidth and resource-heavy constraint and exposes the system to privacy concerns. We instead implement a peer to peer learning system in which nodes train on their own data and periodically perform a weighted average of their parameters with that of their peers according to a learned trust matrix. So far, we have created a model client framework and have been using this to run experiments on the proposed system using multiple virtual nodes which in reality exist on the same computer. We used this strategy as stated in Iteration 1 of our proposal to prove the concept of peer to peer learning with shared parameters. We now hope to run more experiments and build a more deployable real world system for the same.