mlsanityData to 14 Oct 2026

Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretability

arXiv 1904.03867 ↗First posted 8 Apr 2019stat.ML cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Post-hoc model-agnostic interpretation methods such as partial dependence plots can be employed to interpret complex machine learning models. While these interpretation methods can be applied regardless of model complexity, they can produce misleading and verbose results if the model is too complex, especially w.r.t. feature interactions. To quantify the complexity of arbitrary machine learning models, we propose model-agnostic complexity measures based on functional decomposition: number of features used, interaction strength and main effect complexity. We show that post-hoc interpretation of models that minimize the three measures is more reliable and compact. Furthermore, we demonstrate the application of these measures in a multi-objective optimization approach which simultaneously minimizes loss and complexity.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 10; 2023: 5; 2024: 3; 2025: 0; 2026: 1.

22 papers.

Sort:

  1. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 145
  2. 2021YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimizationcited by 62
  3. 2023SHAP-IQ: Unified Approximation of any-order Shapley Interactionscited by 51
  4. 2021Explainable Artificial Intelligence Approaches: A Surveycited by 40
  5. 2024Trust in AI: Progress, Challenges, and Future Directionscited by 35
  6. 2022From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible MLcited by 27
  7. 2022Comparing Explanation Methods for Traditional Machine Learning Models Part 1: An Overview of Current Methods and Quantifying Their Disagreementcited by 14
  8. 2024Position: A Call to Action for a Human-Centered AutoML Paradigmcited by 14
  9. 2022DALE: Differential Accumulated Local Effects for efficient and accurate global explanationscited by 11
  10. 2024Statistical Multicriteria Benchmarking via the GSD-Frontcited by 11
  11. 2023Interpreting and generalizing deep learning in physics-based problems with functional linear modelscited by 9
  12. 2023Improving Interpretability via Explicit Word Interaction Graph Layercited by 6
10 more
  1. 2023Multi-Objective Optimization of Performance and Interpretability of Tabular Supervised Machine Learning Modelscited by 6
  2. 2022Marginal Effects for Non-Linear Prediction Functionscited by 5
  3. 2022Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Modelscited by 5
  4. 2022A Collection of Quality Diversity Optimization Problems Derived from Hyperparameter Optimization of Machine Learning Modelscited by 3
  5. 2022Mind the Gap: Measuring Generalization Performance Across Multiple Objectivescited by 3
  6. 2023Statistical inference using machine learning and classical techniques based on accumulated local effects (ALE)cited by 3
  7. 2022Comparing Explanation Methods for Traditional Machine Learning Models Part 2: Quantifying Model Explainability Faithfulness and Improvements with Dimensionality Reductioncited by 2
  8. 2022Machine Learning Workflow to Explain Black-box Models for Early Alzheimer's Disease Classification Evaluated for Multiple Datasetscited by 1
  9. 2022Application of Machine Learning Methods in Inferring Surface Water Groundwater Exchanges using High Temporal Resolution Temperature Measurementscited by 0
  10. 2026Evaluating Explanation Methods by the Predictors They Inducecited by 0