Method Agnostic Model Class Reliance (MAMCR) Explanation of Multiple Machine Learning Models

Abirami Gunasekaran, Minsi Chen, Richard Hill, Keith McCabe

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

1 Citation (Scopus)

Abstract

Various Explainable Artificial Intelligence (XAI) methods provide insight into the machine learning models by quantitatively analysing the contribution of each variable to the model’s predictions globally or locally. The contribution of variables identified as (un)important by one method’s explanation may not be identified as the same by another method’s explanation for the same machine learning (ML) model. Similarly, the important feature of many well performing ML models that fit equally well on the same data (which are termed as Rashomon set models) may not be the same as each other. While this is the case, providing the explanation based on a single model in the lens of a specific explanation method would be biased over the model/method. Hence, a framework is proposed to describe the consensus variable importance across multiple explanation methods for many almost-equally-accurate models as a method agnostic explanation for the model class reliance. Empirical experiments are carried out on the COMPAS dataset with six XAI (the Sage, Lofo, Shap, Skater, Dalex and iAdditive) methods for verifying whether an inadmissible feature becoming an (un)important feature is consistent across multiple explanation methods and getting the consensus explanation. The results demonstrate the efficiency of the method agnostic model class reliance explanation and its coverage to the model reliance range of all the almost-equally-accurate models of the model class.

Original languageEnglish
Title of host publicationSoft Computing and Its Engineering Applications
Subtitle of host publication4th International Conference, icSoftComp 2022, Proceedings
EditorsKanubhai K. Patel, K.C. Santosh, Atul Patel, Ashish Ghosh
PublisherSpringer, Cham
Pages56-71
Number of pages16
Volume1788
Edition1st
ISBN (Electronic)9783031276095
ISBN (Print)9783031276088
DOIs
Publication statusPublished - 8 Mar 2023
Event4th International Conference on Soft Computing and its Engineering Applications - Anand, India
Duration: 9 Dec 202210 Dec 2022
Conference number: 4

Publication series

NameCommunications in Computer and Information Science
PublisherSpringer Cham
Volume1788 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference4th International Conference on Soft Computing and its Engineering Applications
Abbreviated titleicSoftComp 2022
Country/TerritoryIndia
CityAnand
Period9/12/2210/12/22

Fingerprint

Dive into the research topics of 'Method Agnostic Model Class Reliance (MAMCR) Explanation of Multiple Machine Learning Models'. Together they form a unique fingerprint.

Cite this