How Interpretable and Trustworthy are GAMs?
Abstract
Generalized additive models (GAMs) have become a leading model class for interpretable machine learning. However, there are many algorithms for training GAMs, and these can learn different or even contradictory models, while being equally accurate. Which GAM should we trust? In this paper, we quantitatively and qualitatively investigate a variety of GAM algorithms on real and simulated datasets. We find that GAMs with high feature sparsity (only using a few variables to make predictions) can miss patterns in the data and be unfair to rare subpopulations. Our results suggest that inductive bias plays a crucial role in what interpretable models learn and that tree-based GAMs represent the best balance of sparsity, fidelity and accuracy and thus appear to be the most trustworthy GAM models.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
IG can identify structural elements from classified drugs using CNN.
“Preuer et al. [120] demonstrated that IG can identify these elements from the classified drug using CNN.”
From Explainable, trustworthy, and ethical machine learning for healthcare: A survey (2022) · cites this paper as [120]
Cites
1 retracted
Hunter, P. R., & Prüss‐Üstün, A. (2016) · PLoS ONE · doi:10.1371/journal.pone.0164571 · Cited by 37 · see citing works
RetractedXGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · see citing works
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · see citing works
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 24,190 · see citing works
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · see citing works
Generalized Additive Models: An Introduction with R
Wood, S. N. (2017) · doi:10.1201/9781315370279 · Cited by 13,852 · see citing works
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
Lu, Z. Q. J. (2010) · Journal of the Royal Statistical Society Series A (Statistics in Society) · doi:10.1111/j.1467-985x.2010.00646_6.x · Cited by 12,904 · see citing works
Wood, S. N. (2010) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.1467-9868.2010.00749.x · Cited by 7,538 · see citing works
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682 · see citing works
The mythos of model interpretability
Lipton, Z. C. (2018) · Communications of the ACM · doi:10.1145/3233231 · Cited by 5,427 · see citing works
Spline Models for Observational Data
Wahba, G. (1990) · doi:10.1137/1.9781611970128 · Cited by 4,184 · see citing works
Bias in random forest variable importance measures: Illustrations, sources and a solution
Strobl, C., Boulesteix, A., Zeileis, A., & Hothorn, T. (2007) · BMC Bioinformatics · doi:10.1186/1471-2105-8-25 · Cited by 3,755 · see citing works
Sparsity and Smoothness Via the Fused Lasso
Tibshirani, R. J., Saunders, M. A., Rosset, S., Zhu, J., & Knight, K. (2004) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.1467-9868.2005.00490.x · Cited by 2,643 · see citing works
Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission
Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., & Elhadad, N. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2788613 · Cited by 1,685 · see citing works
Self-citationHierarchical generalized additive models in ecology: an introduction with mgcv
Pedersen, E. J., Miller, D. L., Simpson, G. L., & Ross, N. (2019) · PeerJ · doi:10.7717/peerj.6876 · Cited by 1,225 · see citing works
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Slack, D., Hilgard, S., Jia, E., Singh, S., & Lakkaraju, H. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375830 · Cited by 900 · see citing works
Intelligible models for classification and regression
Lou, Y., Caruana, R., & Gehrke, J. (2012) · Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2339530.2339556 · Cited by 547 · see citing works
Self-citationGeneralized additive models: Building evidence of air pollution, climate change and human health
Ravindra, K., Rattan, P., Mor, S., & Aggarwal, A. N. (2019) · Environment International · doi:10.1016/j.envint.2019.104987 · Cited by 464 · see citing works
Statistical Methods in Medical Research.
Armitage, P., & Berry, G. (1997) · Biometrics · doi:10.2307/2533132 · Cited by 260 · see citing works
Explainable and Interpretable Models in Computer Vision and Machine Learning
Escalante, H. J., Escalera, S., Guyon, I., Baró, X., Güçlütürk, Y., Güçlü, U., & van Gerven, M. (2018) · The Springer series on challenges in machine learning · doi:10.1007/978-3-319-98131-4 · Cited by 203 · see citing works
servén, D., Brummitt, C., Király, F. J., JodesL, Schmitz, D., Carmichael, Z., Ouslan, A., Miccoli, F., IlyesD, Taylor, J., et al. (2018) · Figshare · doi:10.5281/zenodo.1208723 · Cited by 153 · see citing works
Tan, S., Caruana, R., Hooker, G., & Lou, Y. (2018) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3278721.3278725 · Cited by 127 · see citing works
Self-citation(2013) · Statistics and Computing · doi:10.1007/11222.1573-1375 · Cited by 116 · see citing works
Decision Tree Instability and Active Learning
Dwyer, K., & Holte, R. C. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74958-5_15 · Cited by 62 · see citing works
Petersen, A. J., Witten, D., & Simon, N. (2015) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2015.1073155 · Cited by 62 · see citing works
(2022) · Horticulture Research · doi:10.1038/41438.2052-7276 · Cited by 62 · see citing works
On Feature Selection, Bias-Variance, and Bagging
Munson, M. A., & Caruana, R. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04174-7_10 · Cited by 58 · see citing works
Self-citationSplitting on categorical predictors in random forests
Wright, M. N., & König, I. R. (2019) · PeerJ · doi:10.7717/peerj.6339 · Cited by 49 · see citing works
Generalized Additive Models in Business and Economics
Sapra, S. K. (2013) · International Journal of Advanced Statistics and Probability · doi:10.14419/ijasp.v1i3.1022 · Cited by 12 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Explainable, trustworthy, and ethical machine learning for healthcare: A survey
Rasheed, K., Qayyum, A., Ghaly, M., Al-Fuqaha, A., Razi, A., & Qadir, J. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106043 · Cited by 372 · see citing works
Interpretable generalized additive neural networks
Kraus, M., Tschernutter, D., Weinzierl, S., & Zschech, P. (2024) · European Journal of Operational Research · doi:10.1016/j.ejor.2023.06.032 · Cited by 59 · see citing works
Bohlen, L., Rosenberger, J., Hambauer, N., Zähringer, D., Franz, V., Zschech, P., & Kraus, M. (2026) · Health Care Management Science · doi:10.1007/s10729-026-09760-y
- Authors
- Chang, C.-H., Tan, S., Lengerich, B., Goldenberg, A., & Caruana, R.
- Affiliations
- University of Toronto (CA)
- Cornell University (US)
- MIT, Broad Institute, Boston, MA, USA
- Microsoft (United States) (US)
- Venue
- Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining
- Publisher
- ACM
- Published
- 2021-08-14
- Pages
- 95-105
- OpenAlex
- W3171322015
- Cited by
- 66
- References
- 29
- Citations by year
- 2026: 5 · 2025: 19 · 2024: 9 · 2023: 15 · 2022: 12 · 2021: 6
- FWCI
- 4.81
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
- Keywords
- generalized additive models, model interpretability, trustworthiness, feature sparsity, inductive bias, fairness, model fidelity, algorithm comparison
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
