2CP: Decentralized Protocols to Transparently Evaluate Contributivity in Blockchain Federated Learning Environments

11/15/2020
by   Harry Cai, et al.
0

Federated Learning harnesses data from multiple sources to build a single model. While the initial model might belong solely to the actor bringing it to the network for training, determining the ownership of the trained model resulting from Federated Learning remains an open question. In this paper we explore how Blockchains (in particular Ethereum) can be used to determine the evolving ownership of a model trained with Federated Learning. Firstly, we use the step-by-step evaluation metric to assess the relative contributivities of participants in a Federated Learning process. Next, we introduce 2CP, a framework comprising two novel protocols for Blockchained Federated Learning, which both reward contributors with shares in the final model based on their relative contributivity. The Crowdsource Protocol allows an actor to bring a model forward for training, and use their own data to evaluate the contributions made to it. Potential trainers are guaranteed a fair share of the resulting model, even in a trustless setting. The Consortium Protocol gives trainers the same guarantee even when no party owns the initial model and no evaluator is available. We conduct experiments with the MNIST dataset that reveal sound contributivity scores resulting from both Protocols by rewarding larger datasets with greater shares in the model. Our experiments also showed the necessity to pair 2CP with a robust model aggregation mechanism to discard low quality inputs coming from model poisoning attacks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/26/2021

Transparent Contribution Evaluation for Secure Federated Learning on Blockchain

Federated Learning is a promising machine learning paradigm when multipl...
research
11/08/2019

Revocable Federated Learning: A Benchmark of Federated Forest

A learning federation is composed of multiple participants who use the f...
research
08/29/2023

FedChain: An Efficient and Secure Consensus Protocol based on Proof of Useful Federated Learning for Blockchain

Blockchain has become a popular decentralized paradigm for various appli...
research
02/25/2021

Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning

Federated learning is a new learning paradigm that decouples data collec...
research
09/01/2023

Leveraging Learning Metrics for Improved Federated Learning

Currently in the federated setting, no learning schemes leverage the eme...
research
05/10/2021

Latency Analysis of Consortium Blockchained Federated Learning

A decentralized federated learning architecture is proposed to apply to ...
research
06/28/2021

Weight Divergence Driven Divide-and-Conquer Approach for Optimal Federated Learning from non-IID Data

Federated Learning allows training of data stored in distributed devices...

Please sign up or login with your details

Forgot password? Click here to reset