mlsanityData to 7 Oct 2026

Deep Survival Machines: Fully Parametric Survival Regression and Representation Learning for Censored Data with Competing Risks

arXiv 2003.01176 ↗First posted 2 Mar 2020cs.LG stat.AP stat.MLcited by 70

Not on the map. Why?

Abstract (arXiv)

We describe a new approach to estimating relative risks in time-to-event prediction problems with censored data in a fully parametric manner. Our approach does not require making strong assumptions of constant proportional hazard of the underlying survival distribution, as required by the Cox-proportional hazard model. By jointly learning deep nonlinear representations of the input covariates, we demonstrate the benefits of our approach when used to estimate survival risks through extensive experimentation on multiple real world datasets with different levels of censoring. We further demonstrate advantages of our model in the competing risks scenario. To the best of our knowledge, this is the first work involving fully parametric estimation of survival times with competing risks in the presence of censoring.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 16; 2024: 15; 2025: 15; 2026: 12.

70 papers.

Sort:

By area:

  1. 2023MOTOR: A Time-To-Event Foundation Model For Structured Medical Recordscited by 75
  2. 2023Deep Learning for Survival Analysis: A Reviewcited by 75
  3. 2021Deep Cox Mixtures for Survival Regressioncited by 43
  4. 2021SurvTRACE: Transformers for Survival Analysis with Competing Eventscited by 40
  5. 2021A Deep Variational Approach to Clustering Survival Datacited by 25
  6. 2024CoxKAN: Kolmogorov-Arnold Networks for Interpretable, High-Performance Survival Analysiscited by 22
  7. 2023Neural Fine-Gray: Monotonic neural networks for competing riskscited by 20
  8. 2022auton-survival: an Open-Source Package for Regression, Counterfactual Estimation, Evaluation and Phenotyping with Censored Time-to-Event Datacited by 17
  9. 2024An Introduction to Deep Survival Analysis Models for Predicting Time-to-Event Outcomescited by 16
  10. 2022Counterfactual Phenotyping with Censored Time-to-Eventscited by 13
  11. 2023Copula-Based Deep Survival Models for Dependent Censoringcited by 12
  12. 2022Survival Kernets: Scalable and Interpretable Deep Kernel Survival Analysis with an Accuracy Guaranteecited by 9
38 more
  1. 2023DySurv: dynamic deep learning model for survival analysis with conditional variational inferencecited by 9
  2. 2022The Concordance Index decomposition: A measure for a deeper understanding of survival prediction modelscited by 8
  3. 2024HACSurv: A Hierarchical Copula-Based Approach for Survival Analysis with Dependent Competing Riskscited by 7
  4. 2024Survival Models: Proper Scoring Rule and Stochastic Optimization with Competing Riskscited by 6
  5. 2022Survival Seq2Seq: A Survival Model based on Sequence to Sequence Architecturecited by 5
  6. 2024Efficient Training of Probabilistic Neural Networks for Survival Analysiscited by 4
  7. 2024FPBoost: Fully Parametric Gradient Boosting for Survival Analysiscited by 4
  8. 2024Toward a Well-Calibrated Discrimination via Survival Outcome-Aware Contrastive Learningcited by 4
  9. 2022Deep conditional transformation models for survival analysiscited by 3
  10. 2023Deep Clustering Survival Machines with Interpretable Expert Distributionscited by 3
  11. 2023Using Geographic Location-based Public Health Features in Survival Analysiscited by 3
  12. 2024Adaptive Transformer Modelling of Density Function for Nonparametric Survival Analysiscited by 3
  13. 2024MENSA: A Multi-Event Network for Survival Analysis with Trajectory-based Likelihood Estimationcited by 3
  14. 2025Beyond Cox Models: Assessing the Performance of Machine-Learning Methods in Non-Proportional Hazards and Non-Linear Survival Analysiscited by 3
  15. 2026SVL: Goal-Conditioned Reinforcement Learning as Survival Learningcited by 3
  16. 2022Variable selection for nonlinear Cox regression model via deep learningcited by 2
  17. 2023A General Framework for Visualizing Embedding Spaces of Neural Survival Analysis Models Based on Angular Informationcited by 2
  18. 2023Predicting Survival Time of Ball Bearings in the Presence of Censoringcited by 2
  19. 2025SurvUnc: A Meta-Model Based Uncertainty Quantification Framework for Survival Analysiscited by 2
  20. 2025Competing Risks: Impact on Risk Estimation and Algorithmic Fairnesscited by 2
  21. 2022Reverse Survival Model (RSM): A Pipeline for Explaining Predictions of Deep Survival Modelscited by 1
  22. 2023Learning Survival Distribution with Implicit Survival Functioncited by 1
  23. 2023Maximum Likelihood Estimation of Flexible Survival Densities with Importance Samplingcited by 1
  24. 2024SeqRisk: Transformer-augmented latent variable model for robust survival prediction with longitudinal datacited by 1
  25. 2024Deep End-to-End Survival Analysis with Temporal Consistencycited by 1
  26. 2025Censor Dependent Variational Inferencecited by 1
  27. 2025Extending Cox Proportional Hazards Model with Symbolic Non-Linear Log-Risk Functions for Survival Analysiscited by 1
  28. 2025Learning Survival Distributions with the Asymmetric Laplace Distributioncited by 1
  29. 2025Whole-body Representation Learning For Competing Preclinical Disease Risk Assessmentcited by 1
  30. 2025Stepwise Fine and Gray: Subject-Specific Variable Selection Shows When Hemodynamic Data Improves Prognostication of Comatose Post-Cardiac Arrest Patientscited by 1
  31. 2025Let the Experts Speak: Improving Survival Prediction & Calibration via Mixture-of-Experts Headscited by 1
  32. 2026Capture Timing-Attention of Events in Clinical Time Seriescited by 1
  33. 2026Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networkscited by 1
  34. 2026Value-Monotonicity Matters: A Concordance Loss for Deep Survival Predictioncited by 1
  35. 2022Predicting adverse outcomes following catheter ablation treatment for atrial fibrillationcited by 0
  36. 2023Case-Base Neural Networks: survival analysis with time-varying, higher-order interactionscited by 0
  37. 2023Modelling customer churn for the retail industry in a deep learning based sequential frameworkcited by 0
  38. 2023Can-SAVE: Deploying Low-Cost and Population-Scale Cancer Screening via Survival Analysis Variables and EHRcited by 0

50 most cited of 70 All 70 (JSON)