MMCIE: Multi-order Multivariate Coalition Internal-External Interaction for Image Explanation

  • Mingfeng Huang
  • , Guoheng Huang
  • , Xiaomin Zhou
  • , Chi Man Pun
  • , Xuhang Chen
  • , Xiaochen Yuan
  • , Guo Zhong

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

Abstract

Shapley values are extensively utilized in Explainable Artificial Intelligence to interpret predictions made by complex machine learning models. However, much of the research has focused on addressing the costly computational aspects of Shapley values, neglecting the rich interactive knowledge representation inherent in the data within the model. Therefore, MMCIE is proposed in this article, focusing on exploring the conceptual modeling of data by the model. Based on Shapley values, it defines the interaction between inner and outer coalitions to accurately quantify the concept of model modeling. Specifically, the Superpixel Coalitions Selecting Module (SCSM) is proposed, which defines coalitions as entities and paves the way for calculating multivariable interaction values and internal interaction values. Additionally, the Internal and External Interaction Module (IEIM) acts as a bridge, computing and connecting the internal and external interaction values of coalitions, thereby constructing the feature prototype of the model. Moreover, the Multi-order Equidistance Coalitions Modeling Module (MECMM) is introduced as an effective approach to reduce computational complexity and explore the storage methods of the model’s conceptual modeling. Experiments on two datasets show the advantage of MMCIE over existing methods, revealing the model’s concept modeling process through multi-order interactions and offering a fresh view for model interpretation.

Original languageEnglish
Title of host publicationNeural Information Processing - 31st International Conference, ICONIP 2024, Proceedings
EditorsMufti Mahmud, Maryam Doborjeh, Kevin Wong, Andrew Chi Sing Leung, Zohreh Doborjeh, M. Tanveer
PublisherSpringer Science and Business Media Deutschland GmbH
Pages1-15
Number of pages15
ISBN (Print)9789819669479
DOIs
Publication statusPublished - 2025
Event31st International Conference on Neural Information Processing, ICONIP 2024 - Auckland, New Zealand
Duration: 2 Dec 20246 Dec 2024

Publication series

NameCommunications in Computer and Information Science
Volume2282 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference31st International Conference on Neural Information Processing, ICONIP 2024
Country/TerritoryNew Zealand
CityAuckland
Period2/12/246/12/24

Keywords

  • Feature Attribution Methods
  • Shapley Values
  • XAI

Fingerprint

Dive into the research topics of 'MMCIE: Multi-order Multivariate Coalition Internal-External Interaction for Image Explanation'. Together they form a unique fingerprint.

Cite this