Papaya: Federated Learning, but Fully Decentralized
This addresses privacy and efficiency concerns in federated learning for distributed data applications, though it remains incremental as it builds on existing federated learning concepts.
The paper tackles the bandwidth, resource, and privacy limitations of centralized federated learning servers by implementing a fully decentralized peer-to-peer system where nodes train locally and periodically average parameters with peers using a learned trust matrix. They have created a model client framework and run initial proof-of-concept experiments with virtual nodes on a single computer.
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.