# Dual Mixture-of-Experts Framework for Discrete-Time Survival Analysis

arXiv: https://arxiv.org/abs/2510.26014 · HTML: https://mlsanity.com/paper/2510.26014/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts.
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Placed in

- Mixture-of-experts / [Medical and biomedical MoE](https://mlsanity.com/moe/medical-and-biomedical-moe/)

## Builds on (most cited first, 8 of 8)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Domain Adaptive Ensemble Learning](https://mlsanity.com/paper/2003.07325/) (2020)
- [A Scalable Discrete-Time Survival Model for Neural Networks](https://mlsanity.com/paper/1805.00917/) (2018)
- [Multi-Source Domain Adaptation with Mixture of Experts](https://mlsanity.com/paper/1809.02256/) (2018)
- [Deep Recurrent Survival Analysis](https://mlsanity.com/paper/1809.02403/) (2018)
- [SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data](https://mlsanity.com/paper/2110.14001/) (2021)
- [Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation](https://mlsanity.com/paper/2304.01279/) (2023)
- [Toward a Well-Calibrated Discrimination via Survival Outcome-Aware Contrastive Learning](https://mlsanity.com/paper/2410.11340/) (2024)

## Built on by (most cited first, 1 of 1)

- [SVL: Goal-Conditioned Reinforcement Learning as Survival Learning](https://mlsanity.com/paper/2604.17551/) (2026)

## Abstract (arXiv)

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.