Towards more stable LIME for explainable AI

Chung Hou Ng, Hussain Sadiq Abuwala, Chern Hong Lim

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

5 Citations (Scopus)

Abstract

Although AI's development is remarkable, end users do not know how the AI has come to a specific conclusion due to the black-box nature of AI algorithms like deep learning. This has given rise to the field of explainable AI (XAI) where techniques are being developed to explain AI algorithms. One such technique is called Local Interpretable Model-Agnostic Explanations (LIME). LIME is popular because it is modelagnostic and works well with text, tabular and image data. While it has some good features, there are still room for improvements towards the original LIME algorithm especially it's stability. In this work, the LIME stability is being reviewed and three different approaches were investigated for its effectiveness in stability improvement which are; 1) using high sample size for stable ordering, 2) using an averaging method to reduce region flipping; and 3) to evaluate different super-pixels segmentation algorithms in generating stable LIME outcome. The experiment results shows a definite increase in the stability of the improved LIME compared to the baseline LIME and thus the reliability of using it practically.

Original languageEnglish
Title of host publication2022 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2022
EditorsHitoshi Kiya
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages4
ISBN (Electronic)9798350332421
ISBN (Print)9798350332438
DOIs
Publication statusPublished - 2022
EventIEEE International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS) 2022 - Penang, Malaysia
Duration: 22 Nov 202225 Nov 2022
https://ieeexplore.ieee.org/xpl/conhome/10082768/proceeding (Proceedings)
https://web.archive.org/web/20220925073530/https://www.ispacs2022.org/committee.html (Website)

Conference

ConferenceIEEE International Symposium on Intelligent Signal Processing and Communications Systems (ISPACS) 2022
Abbreviated titleISPACS 2022
Country/TerritoryMalaysia
CityPenang
Period22/11/2225/11/22
Internet address

Keywords

  • Explainable AI
  • Explanation Stability
  • LIME
  • Model-Agnostic

Cite this