English  |  正體中文  |  简体中文  |  Items with full text/Total items : 65231/98744 (66%)
Visitors : 31965908      Online Users : 3669
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/128631


    Title: RealExp: Decoupling Correlation Bias in Shapley Values for Faithful Model Interpretations
    Authors: Jiang, W. D.;Chang, C. Y.;Yen, S. J.;Wu, S. J.;Roy, D. S.
    Keywords: Deep learning;Explained artificial intelligence (XAI);Machine learning;Interpretability
    Date: 2025-07
    Issue Date: 2026-03-09 12:05:46 (UTC+8)
    Publisher: Elsevier
    Abstract: Deep learning has achieved significant success in handling unstructured data but remains limited by its "black box" nature, especially in sensitive applications. Existing interpretable machine learning methods partially address this issue but often overlook feature correlations and provide inadequate assessments of model decision paths. To tackle these challenges, this paper introduces Real Explainer (RealExp), a novel interpretability method that decouples the Shapley Value into individual feature importance and feature correlation importance. By integrating feature similarity computations, RealExp enhances interpretability by precisely quantifying both individual contributions and interactions, leading to more reliable explanations. Furthermore, a new interpretability evaluation criterion is proposed, focusing on decision path analysis beyond accuracy-based assessments. Experiments on image classification and sentiment analysis demonstrate RealExp's superiority in interpretability. Case studies highlight its practical benefits: RealExp aids in selecting pre-trained models for pneumonia detection, emphasizes pre-trained video segmentation for anomaly detection, and optimizes text models, achieving performance to RoBERTA finetuning model without pre-trained embeddings.
    Relation: Information Processing & Management 62(4) pp. 104153-104183,
    DOI: 10.1016/j.ipm.2025.104153
    Appears in Collections:[Graduate Institute & Department of Computer Science and Information Engineering] Journal Article

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML69View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback