CoChat

Bias in Cross-Entropy-Based Training of Deep Survival Networks

Zadeh, Shekoufeh Gorgi, Schmid, Matthias · 2021 · IEEE Transactions on Pattern Analysis and Machine Intelligence
Cited by 203

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Abstract

Over the last years, utilizing deep learning for the analysis of survival data has become attractive to many researchers. This has led to the advent of numerous network architectures for the prediction of possibly censored time-to-event variables. Unlike networks for cross-sectional data (used e.g., in classification), deep survival networks require the specification of a suitably defined loss function that incorporates typical characteristics of survival data such as censoring and time-dependent features. Here, we provide an in-depth analysis of the cross-entropy loss function, which is a popular loss function for training deep survival networks. For each time point t, the cross-entropy loss is defined in terms of a binary outcome with levels "event at or before t" and "event after t". Using both theoretical and empirical approaches, we show that this definition may result in a high prediction error and a heavy bias in the predicted survival probabilities. To overcome this problem, we analyze an alternative loss function that is derived from the negative log-likelihood function of a discrete time-to-event model. We show that replacing the cross-entropy loss by the negative log-likelihood loss results in much better calibrated prediction rules and also in an improved discriminatory power, as measured by the concordance index.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2020.2979450

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 7 references

Research works printed but not linked: 18

  1. 10.1109/BIBM.2016.7822579 · DOI · Paper page
  2. 10.1007/978-3-030-01424-7_3 · DOI
  3. lee, 2018, DeepHit: A deep learning approach to survival analysis with competing risks, Proc 32nd AAAI Conf Artif Intell, 2314
  4. 10.1609/aaai.v33i01.33014798 · DOI
  5. 10.1109/CVPR.2017.725 · DOI · Paper page
  6. 10.1038/s42256-019-0019-2 · DOI · Paper page
  7. 10.1002/sim.6428 · DOI · Paper page
  8. 10.1002/sim.5464 · DOI
  9. 10.18637/jss.v050.i11 · DOI · Paper page
  10. 10.1109/TPAMI.2017.2691768 · DOI · Paper page
  11. 10.1001/jama.2018.11103 · DOI · Paper page
  12. 10.1002/sim.4780140108 · DOI · Paper page
  13. 10.1002/sim.5681 · DOI · Paper page
  14. 10.1007/978-3-319-28158-2 · DOI · Paper page
  15. goodfellow, 2016, Deep Learning
  16. 10.1002/9780470094846 · DOI · Paper page
  17. 10.1002/sim.4780030207 · DOI · Paper page
  18. 10.1016/S0140-6736(10)60835-5 · DOI · Paper page

Cited by

See all 203

Metadata

Authors
Zadeh, S. G., & Schmid, M.
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2021-09-01
Volume
43
Issue
9
Pages
3126-3137
ISSN
  • 0162-8828 (ISSN-L)
  • 2160-9292
  • 1939-3539
OpenAlex
W3011132328
Cited by
203
References
7
FWCI
5.59
Type
journal article
Language
en
Open access
closed
Funders
Deutsche Forschungsgemeinschaft (SCHM 2966/2-1)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Bias in Cross-Entropy-Based Training of Deep Survival Networks. https://app.cochat.ai/papers/10.1109/tpami.2020.2979450
The paper
Zadeh, S. G., & Schmid, M. (2021). Bias in Cross-Entropy-Based Training of Deep Survival Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2020.2979450

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.