FedCDC: A Collaborative Framework for Data Consumers in Federated Learning Market

TL;DR

FedCDC introduces a collaborative framework in federated learning markets that detects shared subtasks among Data Consumers, enabling joint training and ensemble distillation to improve model accuracy despite data access restrictions.

Contribution

This work presents a novel framework, FedCDC, for collaborative recruitment and training among Data Consumers with similar tasks in federated learning markets, enhancing performance under data access constraints.

Findings

Joint training mitigates performance loss due to data access restrictions.

Ensemble distillation improves accuracy of Data Consumers' models.

Experimental results show significant accuracy gains with FedCDC.

Abstract

Federated learning (FL) allows machine learning models to be trained on distributed datasets without directly accessing local data. In FL markets, numerous Data Consumers compete to recruit Data Owners for their respective training tasks, but budget constraints and competition can prevent them from securing sufficient data. While existing solutions focus on optimizing one-to-one matching between Data Owners and Data Consumers, we propose \methodname{}, a novel framework that facilitates collaborative recruitment and training for Data Consumers with similar tasks. Specifically, \methodname{} detects shared subtasks among multiple Data Consumers and coordinates the joint training of submodels specialized for these subtasks. Then, through ensemble distillation, these submodels are integrated into each Data Consumer global model. Experimental evaluations on three benchmark datasets demonstrate that restricting Data Consumers access to Data Owners significantly degrades model performance; however, by incorporating \methodname{}, this performance loss is effectively mitigated, resulting in substantial accuracy gains for all participating Data Consumers.