Skip to main navigation Skip to search Skip to main content

AIDE: Antithetical, Intent-based, and Diverse Example-Based Explanations

  • Ikhtiyor Nematov
  • , Dimitris Sacharidis
  • , Katja Hose
  • , Tomer Sagi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

For many use-cases, it is often important to explain the prediction of a black-box model by identifying the most influential training data samples. Existing approaches lack customization for user intent and often provide a homogeneous set of explanation samples, failing to reveal the model's reasoning from different angles. In this paper, we propose AIDE, an approach for providing antithetical (i.e., contrastive), intent-based, diverse explanations for opaque and complex models. AIDE distinguishes three types of explainability intents: interpreting a correct, investigating a wrong, and clarifying an ambiguous prediction. For each intent, AIDE selects an appropriate set of influential training samples that support or oppose the prediction either directly or by contrast. To provide a succinct summary, AIDE uses diversity-aware sampling to avoid redundancy and increase coverage of the training data. We demonstrate the effectiveness of AIDE on image and text classification tasks, in three ways: quantitatively, assessing correctness and continuity; qualitatively, comparing anecdotal evidence from AIDE and other example-based approaches; and via a user study, evaluating multiple aspects of AIDE. The results show that AIDE addresses the limitations of existing methods and exhibits desirable traits for an explainability method.

Original languageEnglish
Title of host publicationProceedings of the 7th AAAI/ACM Conference on AI, Ethics, and Society, AIES 2024
EditorsSanmay Das, Brian Patrick Green, Kush Varshney, Marianna Ganapini, Andrea Renda
PublisherAAAI Press
Pages1051-1062
Number of pages12
ISBN (Electronic)1577358929, 9781577358923
DOIs
StatePublished - 2024
Externally publishedYes
Event7th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, AIES 2024 - San Jose, United States
Duration: 21 Oct 2024 → 23 Oct 2024

Publication series

NameProceedings of the 7th AAAI/ACM Conference on AI, Ethics, and Society, AIES 2024

Conference

Conference7th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, AIES 2024
Country/TerritoryUnited States
CitySan Jose
Period21/10/24 → 23/10/24

Bibliographical note

Publisher Copyright:
Copyright © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'AIDE: Antithetical, Intent-based, and Diverse Example-Based Explanations'. Together they form a unique fingerprint.

Cite this