mlsanityData to 7 Oct 2026

Leveraging Model-based Trees as Interpretable Surrogate Models for Model Distillation

arXiv 2310.03112 ↗First posted 4 Oct 2023stat.ML cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Surrogate models play a crucial role in retrospectively interpreting complex and powerful black box machine learning models via model distillation. This paper focuses on using model-based trees as surrogate models which partition the feature space into interpretable regions via decision rules. Within each region, interpretable models based on additive main effects are used to approximate the behavior of the black box model, striking for an optimal balance between interpretability and performance. Four model-based tree algorithms, namely SLIM, GUIDE, MOB, and CTree, are compared regarding their ability to generate such surrogate models. We investigate fidelity, interpretability, stability, and the algorithms' capability to capture interaction effects through appropriate splits. Based on our comprehensive analyses, we finally provide an overview of user-specific recommendations.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 14 of its 30 references that are in the map. First posted on arXiv 4 Oct 2023.

Builds on

14 of 30 references.

References · 14

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  2. 2017Distilling a Neural Network Into a Soft Decision Treecited by 230
  3. 2018RuleMatrix: Visualizing and Understanding Classifiers with Rulescited by 62
  4. 2021S-LIME: Stabilized-LIME for Model Explanationcited by 52
  5. 2017Interpreting Blackbox Models via Model Extractioncited by 43
  6. 2017The Impact of Random Models on Clustering Similaritycited by 34
  7. 2018Defining Locality for Surrogates in Post-hoc Interpretablitycited by 33
  8. 2020OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithmscited by 30
  9. 2016Model-based Recursive Partitioning for Subgroup Analysescited by 21
  10. 2018Locally Interpretable Models and Effects based on Supervised Partitioning (LIME-SUP)cited by 19
  11. 2022REPID: Regional Effect Plots with implicit Interaction Detectioncited by 17
  12. 2020Surrogate Locally-Interpretable Models with Supervised Machine Learning Algorithmscited by 10
2 more
  1. 2017Fitting Prediction Rule Ensembles with R Package precited by 5
  2. 2019The Power of Unbiased Recursive Partitioning: A Unifying View of CTree, MOB, and GUIDEcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2026Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablationcited by 2
  2. 2025Experiments with Optimal Model Treescited by 1
  3. 2025Explanations Go Linear: Post-hoc Explainability for Tabular Data with Interpretable Meta-Encodingcited by 1
  4. 2025Transparent Adaptive Learning via Data-Centric Multimodal Explainable AIcited by 1
  5. 2025From Actions to Words: Towards Abstractive-Textual Policy Summarization in RLcited by 0
  6. 2026Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effectscited by 0
  7. 2026UNAD+: An Explainable Hybrid Framework for Unknown Network Attack Detectioncited by 0
  8. 2026SAILS: Surrogate-based Analysis of Interactions via Local Effect Smoothscited by 0