Learning Global Transparent Models Consistent with Local Contrastive Explanations

被引:0
|
作者
Pedapati, Tejaswini [1 ]
Balakrishnan, Avinash [1 ]
Shanmugan, Karthikeyan [1 ]
Dhurandhar, Amit [1 ]
机构
[1] IBM Res, Yorktown Hts, NY 10598 USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
There is a rich and growing literature on producing local contrastive/counterfactual explanations for black-box models (e.g. neural networks). In these methods, for an input, an explanation is in the form of a contrast point differing in very few features from the original input and lying in a different class. Other works try to build globally interpretable models like decision trees and rule lists based on the data using actual labels or based on the black-box models predictions. Although these interpretable global models can be useful, they may not be consistent with local explanations from a specific black-box of choice. In this work, we explore the question: Can we produce a transparent global model that is simultaneously accurate and consistent with the local (contrastive) explanations of the black-box model? We introduce a natural local consistency metric that quantifies if the local explanations and predictions of the black-box model are also consistent with the proxy global transparent model. Based on a key insight we propose a novel method where we create custom boolean features from sparse local contrastive explanations of the black-box model and then train a globally transparent model on just these, and showcase empirically that such models have higher local consistency compared with other known strategies, while still being close in performance to models that are trained with access to the original data.
引用
下载
收藏
页数:11
相关论文
共 50 条
  • [1] Consistent Explanations by Contrastive Learning
    Pillai, Vipin
    Koohpayegani, Soroush Abbasi
    Ouligian, Ashley
    Fong, Dennis
    Pirsiavash, Hamed
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 10203 - 10212
  • [2] Global Concept Explanations for Graphs by Contrastive Learning
    Teufel, Jonas
    Friederich, Pascal
    EXPLAINABLE ARTIFICIAL INTELLIGENCE, PT I, XAI 2024, 2024, 2153 : 184 - 208
  • [3] Local-Global Fusion Augmented Graph Contrastive Learning Based on Generative Models
    Jin, Di
    Wang, Zhiqiang
    Huo, Cuiying
    Yu, Zhizhi
    He, Dongxiao
    Huang, Yuxiao
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT IV, KSEM 2023, 2023, 14120 : 56 - 68
  • [4] Trusting deep learning natural-language models via local and global explanations
    Ventura, Francesco
    Greco, Salvatore
    Apiletti, Daniele
    Cerquitelli, Tania
    KNOWLEDGE AND INFORMATION SYSTEMS, 2022, 64 (07) : 1863 - 1907
  • [5] Trusting deep learning natural-language models via local and global explanations
    Francesco Ventura
    Salvatore Greco
    Daniele Apiletti
    Tania Cerquitelli
    Knowledge and Information Systems, 2022, 64 : 1863 - 1907
  • [6] Towards Transparent Robotic Planning via Contrastive Explanations
    Chen, Shenghui
    Boggess, Kayla
    Feng, Lu
    2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2020, : 6593 - 6598
  • [7] Contrastive Learning of Global-Local Video Representations
    Ma, Shuang
    Zeng, Zhaoyang
    McDuff, Daniel
    Song, Yale
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [8] Approximate Inverse Model Explanations (AIME): Unveiling Local and Global Insights in Machine Learning Models
    Nakanishi, Takafumi
    IEEE ACCESS, 2023, 11 : 101020 - 101044
  • [9] Using model explanations to guide deep learning models towards consistent explanations for EHR data
    Watson, Matthew
    Hasan, Bashar Awwad Shiekh
    Al Moubayed, Noura
    SCIENTIFIC REPORTS, 2022, 12 (01)
  • [10] Using model explanations to guide deep learning models towards consistent explanations for EHR data
    Matthew Watson
    Bashar Awwad Shiekh Hasan
    Noura Al Moubayed
    Scientific Reports, 12