Dual Mixture-of-Experts Framework for Discrete-Time Survival Analysis
This work addresses survival analysis for clinical and biomedical research, offering incremental improvements by integrating with existing deep learning pipelines.
The paper tackles the challenge of modeling patient heterogeneity and temporal dynamics in discrete-time survival analysis by proposing a dual mixture-of-experts framework, which improves the time-dependent C-index by up to 0.04 on breast cancer datasets.
Survival analysis is a task to model the time until an event of interest occurs, widely used in clinical and biomedical research. A key challenge is to model patient heterogeneity while also adapting risk predictions to both individual characteristics and temporal dynamics. We propose a dual mixture-of-experts (MoE) framework for discrete-time survival analysis. Our approach combines a feature-encoder MoE for subgroup-aware representation learning with a hazard MoE that leverages patient features and time embeddings to capture temporal dynamics. This dual-MoE design flexibly integrates with existing deep learning based survival pipelines. On METABRIC and GBSG breast cancer datasets, our method consistently improves performance, boosting the time-dependent C-index up to 0.04 on the test sets, and yields further gains when incorporated into the Consurv framework.