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
  • [41] On the transferability of local model-agnostic explanations of machine learning models to unseen data
    Lopez Gonzalez, Alba Maria
    Garcia-Cuesta, Esteban
    IEEE CONFERENCE ON EVOLVING AND ADAPTIVE INTELLIGENT SYSTEMS 2024, IEEE EAIS 2024, 2024, : 243 - 252
  • [42] Why Does My Model Fail? Contrastive Local Explanations for Retail Forecasting
    Lucic, Ana
    Haned, Hinda
    de Rijke, Maarten
    FAT* '20: PROCEEDINGS OF THE 2020 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, 2020, : 90 - 98
  • [43] Streamlining models with explanations in the learning loop
    Lomuscio, Francesco
    Bajardi, Paolo
    Perotti, Alan
    Amparore, Elvio G.
    2022 IEEE 9TH INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA), 2022, : 965 - 974
  • [44] Efficiently Training Intelligible Models for Global Explanations
    Lou, Yin
    Wang, Yongliang
    Liang, Shiwei
    Dong, Yang
    CIKM '20: PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, 2020, : 2637 - 2644
  • [45] Consistent representation via contrastive learning for skin lesion diagnosis
    Wang, Zizhou
    Zhang, Lei
    Shu, Xin
    Wang, Yan
    Feng, Yangqin
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2023, 242
  • [46] Image Template Matching via Dense and Consistent Contrastive Learning
    Li, Bo
    Wu, Lin Yuanbo
    Liu, Deyin
    Chen, Hongyang
    Ye, Yuanxin
    Xie, Xianghua
    2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 1319 - 1324
  • [47] Consistent prototype contrastive learning for weakly supervised person search
    Lin, Huadong
    Yu, Xiaohan
    Zhang, Pengcheng
    Bai, Xiao
    Zheng, Jin
    Journal of Visual Communication and Image Representation, 2024, 105
  • [48] Supervised Contrastive Learning Based on Fusion of Global and Local Features for Remote Sensing Image Retrieval
    Huang, Mengluan
    Dong, Le
    Dong, Weisheng
    Shi, Guangming
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [49] Local-Global History-Aware Contrastive Learning for Temporal Knowledge Graph Reasoning
    Chen, Wei
    Wan, Huaiyu
    Wu, Yuting
    Zhao, Shuyuan
    Cheng, Jiayaqi
    Li, Yuxin
    Lin, Youfang
    Proceedings - International Conference on Data Engineering, 2024, : 733 - 746
  • [50] Global and Local Contrastive Learning for Self-supervised Skeleton-Based Action Recognition
    Hu J.
    Hou Y.
    Guo Z.
    Gao J.
    IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34 (11) : 1 - 1