Heterogeneous Datasets for Federated Survival Analysis Simulation

TL;DR

This paper introduces a novel method to create realistic, heterogeneous datasets for federated survival analysis by splitting existing datasets using Dirichlet-based algorithms, facilitating benchmarking and development.

Contribution

It proposes two Dirichlet-based algorithms for generating heterogeneous federated survival datasets with adjustable heterogeneity levels, addressing the lack of standard benchmarks.

Findings

Algorithms effectively produce diverse heterogeneity levels.

Generated datasets enable reproducible federated survival analysis experiments.

Quantitative and qualitative evaluations validate the dataset splitting methods.

Abstract

Survival analysis studies time-modeling techniques for an event of interest occurring for a population. Survival analysis found widespread applications in healthcare, engineering, and social sciences. However, the data needed to train survival models are often distributed, incomplete, censored, and confidential. In this context, federated learning can be exploited to tremendously improve the quality of the models trained on distributed data while preserving user privacy. However, federated survival analysis is still in its early development, and there is no common benchmarking dataset to test federated survival models. This work provides a novel technique for constructing realistic heterogeneous datasets by starting from existing non-federated datasets in a reproducible way. Specifically, we propose two dataset-splitting algorithms based on the Dirichlet distribution to assign each data sample to a carefully chosen client: quantity-skewed splitting and label-skewed splitting. Furthermore, these algorithms allow for obtaining different levels of heterogeneity by changing a single hyperparameter. Finally, numerical experiments provide a quantitative evaluation of the heterogeneity level using log-rank tests and a qualitative analysis of the generated splits. The implementation of the proposed methods is publicly available in favor of reproducibility and to encourage common practices to simulate federated environments for survival analysis.