Stratified cross-validation for unbiased and privacy-preserving federated learning
arXiv:2001.08090 · doi:10.1093/jamia/ocaa096
Abstract
Large-scale collections of electronic records constitute both an opportunity for the development of more accurate prediction models and a threat for privacy. To limit privacy exposure new privacy-enhancing techniques are emerging such as federated learning which enables large-scale data analysis while avoiding the centralization of records in a unique database that would represent a critical point of failure. Although promising regarding privacy protection, federated learning prevents using some data-cleaning algorithms thus inducing new biases. In this work we focus on the recurrent problem of duplicated records that, if not handled properly, may cause over-optimistic estimations of a model's performances. We introduce and discuss stratified cross-validation, a validation methodology that leverages stratification techniques to prevent data leakage in federated learning settings without relying on demanding deduplication algorithms.
arXiv comment13 pages, 5 figures
References in corpus (10)
- XGBoost: A Scalable Tree Boosting System
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Scalable and accurate deep learning for electronic health records
- Towards Federated Learning at Scale: System Design
- A generic framework for privacy preserving deep learning
- SecureBoost: A Lossless Federated Learning Framework
- Boosting Privately: Privacy-Preserving Federated Extreme Boosting for Mobile Crowdsensing
- Machine learning and AI research for Patient Benefit: 20 Critical Questions on Transparency, Replicability, Ethics and Effectiveness
- Substra: a framework for privacy-preserving, traceable and collaborative Machine Learning
- NIPS - Not Even Wrong? A Systematic Review of Empirically Complete Demonstrations of Algorithmic Effectiveness in the Machine Learning and Artificial Intelligence Literature