From Contrastive to Abductive Explanations and Back Again

被引:36
作者
Ignatiev, Alexey [1 ]
Narodytska, Nina [2 ]
Asher, Nicholas [3 ]
Marques-Silva, Joao [3 ]
机构
[1] Monash Univ, Melbourne, Australia
[2] VMware Res, Palo Alto, CA 94103 USA
[3] CNRS, IRIT, Toulouse, France
来源
AIXIA 2020 - ADVANCES IN ARTIFICIAL INTELLIGENCE | 2021年 / 12414卷
关键词
MINIMAL UNSATISFIABLE SUBSETS; EXPLAINING EXPLANATION; DIAGNOSIS; SETS;
D O I
10.1007/978-3-030-77091-4_21
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Explanations of Machine Learning (ML) models often address a `Why?' question. Such explanations can be related with selecting feature-value pairs which are sufficient for the prediction. Recent work has investigated explanations that address a `Why Not?' question, i.e. finding a change of feature values that guarantee a change of prediction. Given their goals, these two forms of explaining predictions of ML models appear to be mostly unrelated. However, this paper demonstrates otherwise, and establishes a rigorous formal relationship between `Why?' and `Why Not?' explanations. Concretely, the paper proves that, for any given instance, `Why?' explanations are minimal hitting sets of `Why Not?' explanations and vice-versa. Furthermore, the paper devises novel algorithms for extracting and enumerating both forms of explanations.
引用
收藏
页码:335 / 355
页数:21
相关论文
共 78 条
  • [71] "Why Should I Trust You?" Explaining the Predictions of Any Classifier
    Ribeiro, Marco Tulio
    Singh, Sameer
    Guestrin, Carlos
    [J]. KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, : 1135 - 1144
  • [72] Samek W., 2019, EXPLAINABLE INTERPRE, P5, DOI 10.1007/978-3-030-28954-6
  • [73] Schmidt P., 1988, Predicting Recidivism Using Survival Models
  • [74] Shih A, 2019, AAAI CONF ARTIF INTE, P7966
  • [75] Shih A, 2018, PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, P5103
  • [76] Shih Andy, 2018, INT C PROB GRAPH MOD, P427
  • [77] Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks
    Tran, Son N.
    Garcez, Artur S. d'Avila
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (02) : 246 - 258
  • [78] Auction optimization using regression trees and linear models as integer programs
    Verwer, Sicco
    Zhang, Yingqian
    Ye, Qing Chuan
    [J]. ARTIFICIAL INTELLIGENCE, 2017, 244 : 368 - 395