Abstract Interpretation-Based Feature Importance for Support Vector Machines

  • Abhinandan Pal
  • , Francesco Ranzato*
  • , Caterina Urban
  • , Marco Zanella
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We study how a symbolic representation for support vector machines (SVMs) specified by means of abstract interpretation can be exploited for: (1) enhancing the interpretability of SVMs through a novel feature importance measure, called abstract feature importance (AFI), that does not depend in any way on a given dataset or the accuracy of the SVM and is very fast to compute; and (2) certifying individual fairness of SVMs and producing concrete counterexamples when this verification fails. We implemented our methodology and we empirically showed its effectiveness on SVMs based on linear and nonlinear (polynomial and radial basis function) kernels. Our experimental results prove that, independently of the accuracy of the SVM, our AFI measure correlates much strongly with stability of the SVM to feature perturbations than major feature importance measures available in machine learning software such as permutation feature importance, therefore providing better insight into the trustworthiness of SVMs.
Original languageEnglish
Title of host publicationVerification, Model Checking, and Abstract Interpretation
Subtitle of host publication25th International Conference, VMCAI 2024, London, United Kingdom, January 15–16, 2024, Proceedings, Part I
EditorsRayna Dimitrova, Ori Lahav, Sebastian Wolff
PublisherSpringer
Pages27–49
ISBN (Electronic)9783031505249
ISBN (Print)9783031505232
DOIs
Publication statusPublished - 2024
Event25th International Conference on Verification, Model Checking, and Abstract Interpretation - London, United Kingdom
Duration: 15 Jan 202416 Jan 2024

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume14499
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference25th International Conference on Verification, Model Checking, and Abstract Interpretation
Abbreviated titleVMCAI 2024
Country/TerritoryUnited Kingdom
CityLondon
Period15/01/2416/01/24

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Abstract Interpretation-Based Feature Importance for Support Vector Machines'. Together they form a unique fingerprint.

Cite this