Journal article · 2026 · Open access

A Survey on Uncertainty Quantification Methods for Deep Learning

Wenchong He, Zhe Jiang, Tingsong Xiao, Zelin Xu, Yukun Li

ACM Computing Surveys, 58(7), 1–35 · Published 3 February 2026 · DOI 10.1145/3786319

Open full textCite this paper

In brief

“A Survey on Uncertainty Quantification Methods for Deep Learning” is a 2026 journal article by Wenchong He and 4 co-authors, published in ACM Computing Surveys. OpenAlex counts 339 citations as of 22 November 2026. It is open access under a CC BY licence: the full text is free to read at ACM Computing Surveys.

Citations
339
Most cited in
2026 (228)
Field-weighted impact
216.80
References
163
Authors
5

Abstract

Deep neural networks (DNNs) have achieved tremendous success in computer vision, natural language processing, and scientific and engineering domains. However, DNNs can make unexpected, incorrect, yet overconfident predictions, leading to serious consequences in high-stakes applications such as autonomous driving, medical diagnosis, and disaster response. Uncertainty quantification (UQ) estimates the confidence of DNN predictions in addition to their accuracy. In recent years, many UQ methods have been developed for DNNs. It is valuable to systematically categorize these methods and compare their strengths and limitations. Existing surveys mostly categorize UQ methodologies by neural network architecture or Bayesian formulation, while overlooking the uncertainty sources each method addresses, making it difficult to select an appropriate approach in practice. To fill this gap, this article presents a taxonomy of UQ methods for DNNs based on uncertainty sources (e.g., data versus model uncertainty). We summarize the advantages and disadvantages of each category, and illustrate how UQ can be applied to machine learning problems (e.g., active learning, out-of-distribution robustness, and deep reinforcement learning). We also identify future research directions, including UQ for large language models (LLMs), AI-driven scientific simulations, and DNNs with structured outputs.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

He, W., Jiang, Z., Xiao, T., Xu, Z., & Li, Y. (2026). A Survey on Uncertainty Quantification Methods for Deep Learning. ACM Computing Surveys, 58(7), 1–35. https://doi.org/10.1145/3786319

MLA 9

He, Wenchong, et al. “A Survey on Uncertainty Quantification Methods for Deep Learning.” ACM Computing Surveys, vol. 58, no. 7, 2026, pp. 1–35. https://doi.org/10.1145/3786319.

Chicago

He, Wenchong, Zhe Jiang, Tingsong Xiao, Zelin Xu, and Yukun Li. 2026. “A Survey on Uncertainty Quantification Methods for Deep Learning.” ACM Computing Surveys 58 (7): 1–35. https://doi.org/10.1145/3786319.

Harvard

He, W. et al. (2026) ‘A Survey on Uncertainty Quantification Methods for Deep Learning’, ACM Computing Surveys, 58(7), pp. 1–35. doi:10.1145/3786319.

IEEE

W. He, Z. Jiang, T. Xiao, Z. Xu, and Y. Li, “A Survey on Uncertainty Quantification Methods for Deep Learning,” ACM Computing Surveys, vol. 58, no. 7, pp. 1–35, 2026, doi: 10.1145/3786319.

BibTeX

@article{he2026survey,
  title     = {{A Survey on Uncertainty Quantification Methods for Deep Learning}},
  author    = {He, Wenchong and Jiang, Zhe and Xiao, Tingsong and Xu, Zelin and Li, Yukun},
  journal   = {ACM Computing Surveys},
  year      = {2026},
  volume    = {58},
  number    = {7},
  pages     = {1--35},
  doi       = {10.1145/3786319},
  url       = {https://doi.org/10.1145/3786319}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202211
20231010
20242525
20257575
2026228228

Its field-weighted citation impact is 216.80: it has been cited 216.80 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning

  • uncertainty quantification
  • deep neural network
  • Bayesian neural networks
  • model uncertainty
  • data uncertainty
  • active learning (machine learning)
  • out-of-distribution robustness
  • deep reinforcement learning

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

He, W., Jiang, Z., Xiao, T., Xu, Z., & Li, Y. (2026). A Survey on Uncertainty Quantification Methods for Deep Learning. ACM Computing Surveys, 58(7), 1–35. https://doi.org/10.1145/3786319

How many times has this paper been cited?

339 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at ACM Computing Surveys: sign in and open the full text from this page.

Who wrote this paper?

Wenchong He, Zhe Jiang, Tingsong Xiao, Zelin Xu, Yukun Li.

What is the DOI of this paper?

10.1145/3786319, permanently at https://doi.org/10.1145/3786319. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.