mlsanityData to 14 Oct 2026

Improving Decision Sparsity

arXiv 2410.20483 ↗First posted 27 Oct 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Sparsity is a central aspect of interpretability in machine learning. Typically, sparsity is measured in terms of the size of a model globally, such as the number of variables it uses. However, this notion of sparsity is not particularly relevant for decision-making; someone subjected to a decision does not care about variables that do not contribute to the decision. In this work, we dramatically expand a notion of decision sparsity called the Sparse Explanation Value(SEV) so that its explanations are more meaningful. SEV considers movement along a hypercube towards a reference point. By allowing flexibility in that reference and by considering how distances along the hypercube translate to distances in feature space, we can derive sparser and more meaningful explanations for various types of function classes. We present cluster-based SEV and its variant tree-based SEV, introduce a method that improves credibility of explanations, and propose algorithms that optimize decision sparsity in machine learning models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 27 Oct 2024.

Builds on

36 of 53 references.

References · 36

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  6. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  7. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 373
  8. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  9. 2019Interpretable machine learning: definitions, methods, and applicationscited by 305
  10. 2016Rationalizing Neural Predictionscited by 281
  11. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 233
  12. 2016Understanding Neural Networks through Representation Erasurecited by 224
24 more
  1. 2020Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualizationcited by 173
  2. 2019Learning Model-Agnostic Counterfactual Explanations for Tabular Datacited by 146
  3. 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 131
  4. 2019Interpretable Neural Predictions with Differentiable Binary Variablescited by 126
  5. 2019Efficient Search for Diverse Coherent Explanationscited by 111
  6. 2020Generalized and Scalable Optimal Sparse Decision Treescited by 100
  7. 2019Rethinking Cooperative Rationalization: Introspective Extraction and Complement Controlcited by 96
  8. 2019On the Existence of Simpler Machine Learning Modelscited by 89
  9. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 86
  10. 2018Model Agnostic Supervised Local Explanationscited by 83
  11. 2022Exploring the Whole Rashomon Set of Sparse Decision Treescited by 81
  12. 2017Inverse Classification for Comparison-based Interpretability in Machine Learningcited by 50
  13. 2020In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Predictioncited by 42
  14. 2021Fast Sparse Decision Tree Optimization via Reference Ensemblescited by 38
  15. 2021Understanding Interlocking Dynamics of Cooperative Rationalizationcited by 36
  16. 2019Regularizing Black-box Models for Improved Interpretabilitycited by 35
  17. 2022On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbationscited by 32
  18. 2022Sparse Visual Counterfactual Explanations in Image Spacecited by 30
  19. 2023Exploring and Interacting with the Set of Good Sparse Generalized Additive Modelscited by 30
  20. 2016Generalized Inverse Classificationcited by 22
  21. 2022TimberTrek: Exploring and Curating Sparse Decision Trees with Interactive Visualizationcited by 13
  22. 2022Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differcited by 12
  23. 2022FASTER-CE: Fast, Sparse, Transparent, and Robust Counterfactual Explanationscited by 6
  24. 2024Sparse and Faithful Explanations Without Sparse Modelscited by 5

Built on by

Not cited yet.