mlsanityData to 14 Oct 2026

Abstract Interpretation-Based Feature Importance for SVMs

arXiv 2210.12456 ↗First posted 22 Oct 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose a symbolic representation for support vector machines (SVMs) by means of abstract interpretation, a well-known and successful technique for designing and implementing static program analyses. We leverage this abstraction in two ways: (1) to enhance the interpretability of SVMs by deriving a novel feature importance measure, called abstract feature importance (AFI), that does not depend in any way on a given dataset of the accuracy of the SVM and is very fast to compute, and (2) for verifying stability, notably individual fairness, of SVMs and producing concrete counterexamples when the verification fails. We implemented our approach and we empirically demonstrated its effectiveness on SVMs based on linear and non-linear (polynomial and radial basis function) kernels. Our experimental results show that, independently of the accuracy of the SVM, our AFI measure correlates much more strongly with the stability of the SVM to feature perturbations than feature importance measures widely available in machine learning software such as permutation feature importance. It thus gives better insight into the trustworthiness of SVMs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 49 references that are in the map. First posted on arXiv 22 Oct 2022.

Builds on

22 of 49 references.

References · 22

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  5. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  6. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
  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. 2019Algorithms for Verifying Deep Neural Networkscited by 221
  9. 2016Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Modelscited by 213
  10. 2019Explainable Machine Learning in Deploymentcited by 211
  11. 2019Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importancecited by 87
  12. 2016A Confidence-Based Approach for Balancing Fairness and Accuracycited by 73
10 more
  1. 2019Training individually fair ML models with Sensitive Subspace Robustnesscited by 73
  2. 2020Learning Certified Individually Fair Representationscited by 69
  3. 2018Visualizing the Feature Importance for Black Box Modelscited by 55
  4. 2020FR-Train: A Mutual Information-Based Approach to Fair and Robust Trainingcited by 52
  5. 2019Perfectly Parallel Fairness Certification of Neural Networkscited by 42
  6. 2021A Review of Formal Methods applied to Machine Learningcited by 33
  7. 2016Interpretation of Prediction Models Using the Input Gradientcited by 24
  8. 2022Support Vector Machines under Adversarial Label Contaminationcited by 17
  9. 2021Algorithmic Fairness Verification with Graphical Modelscited by 16
  10. 2019Robustness Verification of Support Vector Machinescited by 9

Built on by

Not cited yet.