Proof of Federated Training: Accountable Cross-Network Model Training and Inference

TL;DR

This paper introduces Proof of Federated Training (PoFT), a scalable blockchain-based framework enabling accountable, cross-network federated learning with verifiable model exchange, improving model efficacy with minimal overhead.

Contribution

PoFT is the first architecture to facilitate scalable, cross-chain federated learning using blockchain, embedding models via parameters and enabling verifiable exchanges across networks.

Findings

Cross-chain training significantly improves model efficacy.

PoFT incurs minimal overhead for inter-chain model exchanges.

Implemented and tested on large-scale Amazon EC2 setup.

Abstract

Blockchain has widely been adopted to design accountable federated learning frameworks; however, the existing frameworks do not scale for distributed model training over multiple independent blockchain networks. For storing the pre-trained models over blockchain, current approaches primarily embed a model using its structural properties that are neither scalable for cross-chain exchange nor suitable for cross-chain verification. This paper proposes an architectural framework for cross-chain verifiable model training using federated learning, called Proof of Federated Training (PoFT), the first of its kind that enables a federated training procedure span across the clients over multiple blockchain networks. Instead of structural embedding, PoFT uses model parameters to embed the model over a blockchain and then applies a verifiable model exchange between two blockchain networks for cross-network model training. We implement and test PoFT over a large-scale setup using Amazon EC2 instances and observe that cross-chain training can significantly boosts up the model efficacy. In contrast, PoFT incurs marginal overhead for inter-chain model exchanges.