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

• URL: http://arxiv.org/abs/2510.26014v1
• Date: Wed, 29 Oct 2025 23:11:01 GMT
• Title: Dual Mixture-of-Experts Framework for Discrete-Time Survival Analysis
• Authors: Hyeonjun Lee, Hyungseob Shin, Gunhee Nam, Hyeonsoo Lee,
• Abstract summary: We propose a dual mixture-of-experts (MoE) framework for discrete-time survival analysis.<n>Our approach combines a feature-encoder MoE for subgroup-aware representation learning with a hazard MoE.<n>On METABRIC and GBSG breast cancer datasets, our method consistently improves performance.
• Score: 3.466900599881846
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Counterfactual Understanding via Retrieval-aware Multimodal Modeling for Time-to-Event Survival Prediction [1.5713805841057418]
  CURE is a framework that advances counterfactual survival modeling via comprehensive multimodal embedding and latent retrieval.<n> Experimental results on METABRIC and TCGA-LUAD datasets demonstrate that proposed CURE model consistently outperforms strong baselines in survival analysis.
  arXiv  Detail & Related papers  (2026-02-23T15:53:25Z)
• Independent Component Discovery in Temporal Count Data [46.526610368455096]
  We introduce a generative framework for independent component analysis of temporal count data, combining regime-adaptive dynamics with Poisson log-normal emissions.<n>The model identifies disentangled components with regime-dependent contributions, enabling representation learning and perturbations analysis.
  arXiv  Detail & Related papers  (2026-01-29T13:30:10Z)
• Exploring Cumulative Effects in Survival Data Using Deep Learning Networks [0.0]
  We introduce CENNSurv, a novel deep learning approach that captures dynamic risk relationships from time-dependent data.<n>CENNSurv revealed a multi-year lagged association between chronic environmental exposure and a critical survival outcome, as well as a critical short-term behavioral shift prior to subscription lapse.
  arXiv  Detail & Related papers  (2025-12-29T00:22:12Z)
• Machine Learning Approaches to Clinical Risk Prediction: Multi-Scale Temporal Alignment in Electronic Health Records [2.9576397177561087]
  This study proposes a risk prediction method based on a Multi-Scale Temporal Alignment Network (MSTAN)<n>It addresses the challenges of temporal irregularity, sampling interval differences, and multi-scale dynamic dependencies in Electronic Health Records (EHR)<n> Experiments conducted on publicly available EHR datasets show that the proposed model outperforms mainstream baselines in accuracy, recall, precision, and F1-Score.
  arXiv  Detail & Related papers  (2025-11-26T16:33:59Z)
• SigBERT: Combining Narrative Medical Reports and Rough Path Signature Theory for Survival Risk Estimation in Oncology [1.5425688173297465]
  SigBERT is an innovative temporal survival analysis framework designed to process a large number of clinical reports per patient.<n>It processes timestamped medical reports by extracting and averaging word embeddings into sentence embeddings.<n>It was trained and evaluated on a real-world oncology dataset from the L'eon B'erard Center corpus, with a C-index score of 0.75 (sd 0.014) on the independent test cohort.
  arXiv  Detail & Related papers  (2025-07-25T12:33:25Z)
• Deep Survival Analysis in Multimodal Medical Data: A Parametric and Probabilistic Approach with Competing Risks [47.19194118883552]
  We introduce a multimodal deep learning framework for survival analysis capable of modeling both single and competing risks scenarios.<n>We propose SAMVAE (Survival Analysis Multimodal Variational Autoencoder), a novel deep learning architecture designed for survival prediction.
  arXiv  Detail & Related papers  (2025-07-10T14:29:48Z)
• Multi-Modal Mamba Modeling for Survival Prediction (M4Survive): Adapting Joint Foundation Model Representations [0.6990493129893112]
  M4Survive is a novel framework that learns joint foundation model representations using efficient adapter networks.<n>By leveraging Mamba-based adapters, M4Survive enables efficient multi-modal learning while preserving computational efficiency.<n>This work underscores the potential of foundation model-driven multi-modal fusion in advancing precision oncology and predictive analytics.
  arXiv  Detail & Related papers  (2025-03-13T05:18:32Z)
• CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis [50.56875995511431]
  We introduce a Cross-Modal Temporal Pattern Discovery (CTPD) framework, designed to efficiently extract meaningful cross-modal temporal patterns from multimodal EHR data.<n>Our approach introduces shared initial temporal pattern representations which are refined using slot attention to generate temporal semantic embeddings.
  arXiv  Detail & Related papers  (2024-11-01T15:54:07Z)
• Deep End-to-End Survival Analysis with Temporal Consistency [49.77103348208835]
  We present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. A central idea in our method is temporal consistency, a hypothesis that past and future outcomes in the data evolve smoothly over time. Our framework uniquely incorporates temporal consistency into large datasets by providing a stable training signal.
  arXiv  Detail & Related papers  (2024-10-09T11:37:09Z)
• Clustering Survival Data using a Mixture of Non-parametric Experts [0.0]
  This study introduces SurvMixClust, a novel algorithm for survival analysis that integrates clustering with survival function prediction. Our evaluations on five public datasets show that SurvMixClust creates balanced clusters with distinct survival curves, outperforms clustering baselines, and competes with non-clustering survival models in predictive accuracy.
  arXiv  Detail & Related papers  (2024-05-24T20:47:58Z)
• Advancing Head and Neck Cancer Survival Prediction via Multi-Label Learning and Deep Model Interpretation [7.698783025721071]
  We propose IMLSP, an Interpretable Multi-Label multi-modal deep Survival Prediction framework for predicting multiple HNC survival outcomes simultaneously. We also present Grad-TEAM, a Gradient-weighted Time-Event Activation Mapping approach specifically developed for deep survival model visual explanation.
  arXiv  Detail & Related papers  (2024-05-09T01:30:04Z)
• USTEP: Spatio-Temporal Predictive Learning under A Unified View [62.58464029270846]
  We introduce USTEP (Unified S-TEmporal Predictive learning), an innovative framework that reconciles the recurrent-based and recurrent-free methods by integrating both micro-temporal and macro-temporal scales.
  arXiv  Detail & Related papers  (2023-10-09T16:17:42Z)
• Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation [48.267001230607306]
  We propose a pretraining framework that enhances multiscale consistency in EM volumes. Our approach leverages a Siamese network architecture, integrating strong and weak data augmentations. It effectively captures voxel and feature consistency, showing promise for learning transferable representations for EM analysis.
  arXiv  Detail & Related papers  (2023-08-19T05:49:13Z)
• Deep Bayesian Active Learning for Accelerating Stochastic Simulation [74.58219903138301]
  Interactive Neural Process (INP) is a deep active learning framework for simulations and with active learning approaches. For active learning, we propose a novel acquisition function, Latent Information Gain (LIG), calculated in the latent space of NP based models. The results demonstrate STNP outperforms the baselines in the learning setting and LIG achieves the state-of-the-art for active learning.
  arXiv  Detail & Related papers  (2021-06-05T01:31:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.