Federated Survival Forests

TL;DR

This paper introduces FedSurF, a federated survival analysis algorithm based on random survival forests, achieving high discriminative power with minimal communication rounds while handling real-world data challenges.

Contribution

The paper presents FedSurF, a novel federated survival analysis method that combines the advantages of random forests with federated learning, requiring only one communication round.

Findings

FedSurF achieves comparable discriminative power to deep learning models with fewer communication rounds.

FedSurF outperforms state-of-the-art federated survival models in non-i.i.d. data environments.

FedSurF maintains low computational cost and handles missing data effectively.

Abstract

Survival analysis is a subfield of statistics concerned with modeling the occurrence time of a particular event of interest for a population. Survival analysis found widespread applications in healthcare, engineering, and social sciences. However, real-world applications involve survival datasets that are distributed, incomplete, censored, and confidential. In this context, federated learning can tremendously improve the performance of survival analysis applications. Federated learning provides a set of privacy-preserving techniques to jointly train machine learning models on multiple datasets without compromising user privacy, leading to a better generalization performance. However, despite the widespread development of federated learning in recent AI research, few studies focus on federated survival analysis. In this work, we present a novel federated algorithm for survival analysis based on one of the most successful survival models, the random survival forest. We call the proposed method Federated Survival Forest (FedSurF). With a single communication round, FedSurF obtains a discriminative power comparable to deep-learning-based federated models trained over hundreds of federated iterations. Moreover, FedSurF retains all the advantages of random forests, namely low computational cost and natural handling of missing values and incomplete datasets. These advantages are especially desirable in real-world federated environments with multiple small datasets stored on devices with low computational capabilities. Numerical experiments compare FedSurF with state-of-the-art survival models in federated networks, showing how FedSurF outperforms deep-learning-based federated algorithms in realistic environments with non-identically distributed data.