CoChat

Interpretable machine learning: Fundamental principles and 10 grand challenges

Open access

The DOI matches its Crossref record; 335 of the 335 references it cites were found in a registry or an index.

Abstract

Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this crucial topic. We also identify 10 technical challenge areas in interpretable machine learning and provide history and background on each problem. Some of these problems are classically important, and some are recent problems that have arisen in the last few years. These problems are: (1) Optimizing sparse logical models such as decision trees; (2) Optimization of scoring systems; (3) Placing constraints into generalized additive models to encourage sparsity and better interpretability; (4) Modern case-based reasoning, including neural networks and matching for causal inference; (5) Complete supervised disentanglement of neural networks; (6) Complete or even partial unsupervised disentanglement of neural networks; (7) Dimensionality reduction for data visualization; (8) Machine learning models that can incorporate physics and other generative or causal constraints; (9) Characterization of the “Rashomon set” of good models; and (10) Interpretable reinforcement learning. This survey is suitable as a starting point for statisticians and computer scientists interested in working in interpretable machine learning.

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 · 10.1214/21-ss133

Cites

335 of 335 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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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

Items 201–335 of 335

Research works printed but not linked: 15

  1. Bousquet, O. and Elisseeff, A. (2002). Stability and generalization. Journal of Machine Learning Research 2 499–526.
  2. Dobkin, D., Fulton, T., Gunopulos, D., Kasif, S. and Salzberg, S. (1997). Induction of shallow decision trees. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  3. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y. (2014). Generative Adversarial Nets. In Proceedings of Conference on Neural Information Processing Systems (NeurIPS) 27 2672–2680.
  4. Hammond, K. (1989). Proceedings of the Second Case-Based Reasoning Workshop (DARPA). Morgan Kanfmann Publishers, Inc., San Mateo, CA.
  5. Hu, X., Rudin, C. and Seltzer, M. (2019). Optimal Sparse Decision Trees. In Proceedings of Conference on Neural Information Processing Systems (NeurIPS).
  6. Juozapaitis, Z., Koul, A., Fern, A., Erwig, M. and Doshi-Velez, F. (2019). Explainable reinforcement learning via reward decomposition. In Proceedings of the IJCAI/ECAI Workshop on Explainable Artificial Intelligence.
  7. Kodratoff, Y. (1994). The comprehensibility manifesto. KDD Nugget Newsletter 94.
  8. Kolodner, J. L. (1988). Proceedings of the Case-Based Reasoning Workshop (DARPA). Morgan Kaufmmnn Publishers, Inc., San Mateo, CA.
  9. Kosiorek, A., Sabour, S., Teh, Y. W. and Hinton, G. E. (2019). Stacked capsule autoencoders. In Proceedings of Conference on Neural Information Processing Systems (NeurIPS) 15512–15522.
  10. Quinlan, J. R. (1993). C4.5: Programs for Machine Learning. Morgan Kaufmann.
  11. Sabour, S., Frosst, N. and Hinton, G. E. (2017). Dynamic routing between capsules. In Proceedings of Conference on Neural Information Processing Systems (NeurIPS) 3856–3866.
  12. Srebro, N., Sridharan, K. and Tewari, A. (2010). Smoothness, low noise and fast rates. In Proceedings of Conference on Neural Information Processing Systems (NeurIPS) 2199–2207.
  13. Yang, H., Rudin, C. and Seltzer, M. (2017). Scalable Bayesian rule lists. In Proceedings of International Conference on Machine Learning (ICML) 3921–3930. · DOI
  14. Zhu, Z., Luo, P., Wang, X. and Tang, X. (2014). Multi-view perceptron: a deep model for learning face identity and view representations. In Proceedings of Conference on Neural Information Processing Systems (NeurIPS) 217–225.
  15. Hastie, T. J. and Tibshirani, R. J. (1990). Generalized additive models 43. CRC press.

Cited by

See all 958

Metadata

Authors
Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., & Zhong, C.
Venue
Statistics Surveys
Published
2022-01-01
Volume
16
Issue
none
Pages
1-85
ISSN
1935-7516 (ISSN-L)
OpenAlex
W3137125108
Cited by
958
References
335
Citations by year
2026: 202 · 2025: 247 · 2024: 205 · 2023: 179 · 2022: 91
FWCI
59.17
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Statistics Surveys (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Science Foundation (1934964, 2022040)
  • U.S. Department of Energy (DESC0021358)
  • National Institute on Drug Abuse (DA054994-01)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
  • Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
Keywords
model interpretability, decision tree, scoring system, generalized additive models, case-based reasoning, dimensionality reduction, physics-informed machine learning, Rashomon set, interpretable reinforcement learning

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

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.