mlsanityData to 7 Oct 2026

Accuracy, Interpretability, and Differential Privacy via Explainable Boosting

arXiv 2106.09680 ↗First posted 17 Jun 2021cs.LG cs.CRcited by 24

Not on the map. Why?

Abstract (arXiv)

We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while protecting privacy. Our experiments on multiple classification and regression datasets show that DP-EBM models suffer surprisingly little accuracy loss even with strong differential privacy guarantees. In addition to high accuracy, two other benefits of applying DP to EBMs are: a) trained models provide exact global and local interpretability, which is often important in settings where differential privacy is needed; and b) the models can be edited after training without loss of privacy to correct errors which DP noise may have introduced.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 16 of its 41 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

16 of 41 references.

References · 16

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  4. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  5. 2013The Composition Theorem for Differential Privacycited by 290
  6. 2019InterpretML: A Unified Framework for Machine Learning Interpretabilitycited by 243
  7. 2019Deep Learning with Gaussian Differential Privacycited by 112
  8. 2018Private Selection from Private Candidatescited by 75
  9. 2019Diffprivlib: The IBM Differential Privacy Librarycited by 51
  10. 2020How Interpretable and Trustworthy are GAMs?cited by 44
  11. 2020In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Predictioncited by 42
  12. 2019Privacy-Preserving Gradient Boosting Decision Treescited by 20
4 more
  1. 2016Decision Tree Classification with Differential Privacy: A Surveycited by 17
  2. 2015Differentially Private Bayesian Optimizationcited by 12
  3. 2015Private Approximations of the 2nd-Moment Matrix Using Existing Techniques in Linear Regressioncited by 8
  4. 2020Scalable and Provably Accurate Algorithms for Differentially Private Distributed Decision Tree Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 9; 2024: 3; 2025: 5; 2026: 1.

24 papers.

Sort:

By area:

  1. 2022Differentially Private Estimation of Heterogeneous Causal Effectscited by 14
  2. 2022TimberTrek: Exploring and Curating Sparse Decision Trees with Interactive Visualizationcited by 13
  3. 2022Federated Boosted Decision Trees with Differential Privacycited by 9
  4. 2024Quantum Gradient Class Activation Map for Model Interpretabilitycited by 9
  5. 2022Differentially Private Optimizers Can Learn Adversarially Robust Modelscited by 6
  6. 2023Improved Differentially Private Regression via Gradient Boostingcited by 6
  7. 2023Interpretable Survival Analysis for Heart Failure Risk Predictioncited by 6
  8. 2023SoK: Unintended Interactions among Machine Learning Defenses and Riskscited by 6
  9. 2023Classification with Partially Private Featurescited by 4
  10. 2021Attention-like feature explanation for tabular datacited by 3
  11. 2025Additive Models Explained: A Computational Complexity Approachcited by 3
  12. 2022Spending Privacy Budget Fairly and Wiselycited by 2
12 more
  1. 2024Automation of Quantum Dot Measurement Analysis via Explainable Machine Learningcited by 2
  2. 2024Differential Privacy for Anomaly Detection: Analyzing the Trade-off Between Privacy and Explainabilitycited by 2
  3. 2025Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Reviewcited by 2
  4. 2025Model Agnostic Differentially Private Causal Inferencecited by 2
  5. 2023The Computational Complexity of Concise Hypersphere Classificationcited by 1
  6. 2025Towards the Formalization of a Trustworthy AI for Mining Interpretable Models explOiting Sophisticated Algorithmscited by 1
  7. 2026Explanations Leak: Membership Inference with Differential Privacy and Active Learning Defensecited by 1
  8. 2023Estimate Deformation Capacity of Non-Ductile RC Shear Walls using Explainable Boosting Machinecited by 0
  9. 2023Smoothly Giving up: Robustness for Simple Modelscited by 0
  10. 2023An explainable model to support the decision about the therapy protocol for AMLcited by 0
  11. 2023S-BDT: Distributed Differentially Private Boosted Decision Treescited by 0
  12. 2025GL-ICNN: An End-To-End Interpretable Convolutional Neural Network for the Diagnosis and Prediction of Alzheimer's Diseasecited by 0