Let the Experts Speak: Improving Survival Prediction & Calibration via Mixture-of-Experts Heads

• URL: http://arxiv.org/abs/2511.09567v1
• Date: Fri, 14 Nov 2025 01:00:15 GMT
• Title: Let the Experts Speak: Improving Survival Prediction & Calibration via Mixture-of-Experts Heads
• Authors: Todd Morrill, Aahlad Puli, Murad Megjhani, Soojin Park, Richard Zemel,
• Abstract summary: We introduce several discrete-time deep mixture-of-experts (MoE) based architectures for survival analysis problems.<n>One of which achieves all desiderata: clustering, calibration, and predictive accuracy.<n>We find that more expressive experts that tailor predictions per patient outperform experts that rely on fixed group prototypes.
• Score: 2.962208518434558
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep mixture-of-experts models have attracted a lot of attention for survival analysis problems, particularly for their ability to cluster similar patients together. In practice, grouping often comes at the expense of key metrics such calibration error and predictive accuracy. This is due to the restrictive inductive bias that mixture-of-experts imposes, that predictions for individual patients must look like predictions for the group they're assigned to. Might we be able to discover patient group structure, where it exists, while improving calibration and predictive accuracy? In this work, we introduce several discrete-time deep mixture-of-experts (MoE) based architectures for survival analysis problems, one of which achieves all desiderata: clustering, calibration, and predictive accuracy. We show that a key differentiator between this array of MoEs is how expressive their experts are. We find that more expressive experts that tailor predictions per patient outperform experts that rely on fixed group prototypes.

Related papers

• Deep Variational Contrastive Learning for Joint Risk Stratification and Time-to-Event Estimation [9.592144785458443]
  CONVERSE is a deep survival model that unifies variational autoencoders with contrastive learning for interpretable risk stratification.<n>It achieves competitive or superior performance compared to existing deep survival methods, while maintaining meaningful patient stratification.
  arXiv  Detail & Related papers  (2026-02-01T18:07:40Z)
• Conformal Set-based Human-AI Complementarity with Multiple Experts [1.1510009152620668]
  This study focuses on the selection of instance-specific experts from a pool of multiple human experts.<n>We introduce a greedy algorithm that utilizes conformal sets to identify the subset of expert predictions that will be used in classifying an instance.
  arXiv  Detail & Related papers  (2025-08-09T14:17:51Z)
• On Arbitrary Predictions from Equally Valid Models [49.56463611078044]
  Model multiplicity refers to multiple machine learning models that admit conflicting predictions for the same patient.<n>We show that even small ensembles can mitigate/eliminate predictive multiplicity in practice.
  arXiv  Detail & Related papers  (2025-07-25T16:15:59Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)
• Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study [65.11303133775857]
  Mixture-of-Experts (MoE) computation amalgamates predictions from several specialized sub-models (referred to as experts) Sparse MoE selectively engages only a limited number, or even just one expert, significantly reducing overhead while empirically preserving, and sometimes even enhancing, performance.
  arXiv  Detail & Related papers  (2024-03-26T05:48:02Z)
• Towards Calibrated Deep Clustering Network [60.71776081164377]
  In deep clustering, the estimated confidence for a sample belonging to a particular cluster greatly exceeds its actual prediction accuracy.<n>We propose a novel dual head (calibration head and clustering head) deep clustering model that can effectively calibrate the estimated confidence and the actual accuracy.<n>The proposed calibrated deep clustering model not only surpasses the state-of-the-art deep clustering methods by 5x on average in terms of expected calibration error, but also significantly outperforms them in terms of clustering accuracy.
  arXiv  Detail & Related papers  (2024-03-04T11:23:40Z)
• Enhancing Molecular Property Prediction via Mixture of Collaborative Experts [23.388085838279405]
  We introduce the GNN-MoCE architecture to address data scarcity and imbalance in MPP. It employs the Mixture of Collaborative Experts (MoCE) as predictors, exploiting task commonalities. Our model demonstrates superior performance over traditional methods on 24 MPP datasets.
  arXiv  Detail & Related papers  (2023-12-06T05:02:10Z)
• MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection [18.059899772411033]
  We find that na"ively combining expert object detectors in a similar way to Deep Ensembles, can often lead to degraded performance. We identify that the primary cause of this issue is that the predictions of the experts do not match their performance. To address this, when constructing the Mixture of Experts, we propose to combine their predictions in a manner which reflects the individual performance of the experts.
  arXiv  Detail & Related papers  (2023-09-26T14:52:51Z)
• Ambiguous Medical Image Segmentation using Diffusion Models [60.378180265885945]
  We introduce a single diffusion model-based approach that produces multiple plausible outputs by learning a distribution over group insights. Our proposed model generates a distribution of segmentation masks by leveraging the inherent sampling process of diffusion. Comprehensive results show that our proposed approach outperforms existing state-of-the-art ambiguous segmentation networks.
  arXiv  Detail & Related papers  (2023-04-10T17:58:22Z)
• Test-time Collective Prediction [73.74982509510961]
  Multiple parties in machine learning want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of agents, but may not be willing to release their data or model parameters. We explore a decentralized mechanism to make collective predictions at test time, leveraging each agent's pre-trained model.
  arXiv  Detail & Related papers  (2021-06-22T18:29:58Z)
• Gaussian Experts Selection using Graphical Models [7.530615321587948]
  Local approximations reduce time complexity by dividing the original dataset into subsets and training a local expert on each subset. We leverage techniques from the literature on undirected graphical models, using sparse precision matrices that encode conditional dependencies between experts to select the most important experts.
  arXiv  Detail & Related papers  (2021-02-02T14:12:11Z)
• Leveraging Expert Consistency to Improve Algorithmic Decision Support [62.61153549123407]
  We explore the use of historical expert decisions as a rich source of information that can be combined with observed outcomes to narrow the construct gap. We propose an influence function-based methodology to estimate expert consistency indirectly when each case in the data is assessed by a single expert. Our empirical evaluation, using simulations in a clinical setting and real-world data from the child welfare domain, indicates that the proposed approach successfully narrows the construct gap.
  arXiv  Detail & Related papers  (2021-01-24T05:40:29Z)
• Survival Cluster Analysis [93.50540270973927]
  There is an unmet need in survival analysis for identifying subpopulations with distinct risk profiles. An approach that addresses this need is likely to improve characterization of individual outcomes.
  arXiv  Detail & Related papers  (2020-02-29T22:41:21Z)

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.