The skyline of counterfactual explanations for machine learning decision models

Counterfactual explanations are minimum changes of a given input to alter the original prediction by a machine learning model, usually from an undesirable prediction to a desirable one. Previous works frame this problem as a constrained cost minimization, where the cost is defined as L1/L2 distance...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, Yongjie, Ding, Qinxu, Wang, Ke, Liu, Yue, Wu, Xingyu, Wang, Jinglong, Liu, Yong, Miao, Chunyan
Other Authors: School of Computer Science and Engineering
Format: Conference or Workshop Item
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/156946
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-156946
record_format dspace
spelling sg-ntu-dr.10356-1569462023-05-26T15:35:46Z The skyline of counterfactual explanations for machine learning decision models Wang, Yongjie Ding, Qinxu Wang, Ke Liu, Yue Wu, Xingyu Wang, Jinglong Liu, Yong Miao, Chunyan School of Computer Science and Engineering 30th ACM International Conference on Information & Knowledge Management (CIKM '21) Alibaba-NTU Singapore Joint Research Institute Engineering::Computer science and engineering Counterfactual Explanations Multi-Objective Optimization Counterfactual explanations are minimum changes of a given input to alter the original prediction by a machine learning model, usually from an undesirable prediction to a desirable one. Previous works frame this problem as a constrained cost minimization, where the cost is defined as L1/L2 distance (or variants) over multiple features to measure the change. In real-life applications, features of different types are hardly comparable and it is difficult to measure the changes of heterogeneous features by a single cost function. Moreover, existing approaches do not support interactive exploration of counterfactual explanations. To address above issues, we propose the skyline counterfactual explanations that define the skyline of counterfactual explanations as all non-dominated changes. We solve this problem as multi-objective optimization over actionable features. This approach does not require any cost function over heterogeneous features. With the skyline, the user can interactively and incrementally refine their goals on the features and magnitudes to be changed, especially when lacking prior knowledge to express their needs precisely. Intensive experiment results on three real-life datasets demonstrate that the skyline method provides a friendly way for finding interesting counterfactual explanations, and achieves superior results compared to the state-of-the-art methods. AI Singapore National Research Foundation (NRF) Submitted/Accepted version This research is supported, in part, by Alibaba Group through Alibaba Innovative Research (AIR) Program and Alibaba-NTU Singapore Joint Research Institute (JRI), Nanyang Technological University, Singapore. This research is also supported, in part, by the National Research Foundation, Prime Minister’s Office, Singapore under its AI Singapore Programme (AISG Award No: AISG-GC2019-003) and under its NRF Investigatorship Programme (NRFI Award No. NRF-NRFI05-2019-0002). The work of Ke Wang is partially supported by a Discovery Grant from Natural Sciences and Engineering Research Council of Canada. 2022-05-10T08:42:35Z 2022-05-10T08:42:35Z 2021 Conference Paper Wang, Y., Ding, Q., Wang, K., Liu, Y., Wu, X., Wang, J., Liu, Y. & Miao, C. (2021). The skyline of counterfactual explanations for machine learning decision models. 30th ACM International Conference on Information & Knowledge Management (CIKM '21), 2030-2039. https://dx.doi.org/10.1145/3459637.3482397 9781450384469 https://hdl.handle.net/10356/156946 10.1145/3459637.3482397 2-s2.0-85119194064 2030 2039 en AISG-GC2019-003 NRF-NRFI05-2019-0002 © 2021 Association for Computing Machinery. All rights reserved. This paper was published in the Proceedings of 30th ACM International Conference on Information & Knowledge Management (CIKM '21) and is made available with permission of Association for Computing Machinery. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Counterfactual Explanations
Multi-Objective Optimization
spellingShingle Engineering::Computer science and engineering
Counterfactual Explanations
Multi-Objective Optimization
Wang, Yongjie
Ding, Qinxu
Wang, Ke
Liu, Yue
Wu, Xingyu
Wang, Jinglong
Liu, Yong
Miao, Chunyan
The skyline of counterfactual explanations for machine learning decision models
description Counterfactual explanations are minimum changes of a given input to alter the original prediction by a machine learning model, usually from an undesirable prediction to a desirable one. Previous works frame this problem as a constrained cost minimization, where the cost is defined as L1/L2 distance (or variants) over multiple features to measure the change. In real-life applications, features of different types are hardly comparable and it is difficult to measure the changes of heterogeneous features by a single cost function. Moreover, existing approaches do not support interactive exploration of counterfactual explanations. To address above issues, we propose the skyline counterfactual explanations that define the skyline of counterfactual explanations as all non-dominated changes. We solve this problem as multi-objective optimization over actionable features. This approach does not require any cost function over heterogeneous features. With the skyline, the user can interactively and incrementally refine their goals on the features and magnitudes to be changed, especially when lacking prior knowledge to express their needs precisely. Intensive experiment results on three real-life datasets demonstrate that the skyline method provides a friendly way for finding interesting counterfactual explanations, and achieves superior results compared to the state-of-the-art methods.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Wang, Yongjie
Ding, Qinxu
Wang, Ke
Liu, Yue
Wu, Xingyu
Wang, Jinglong
Liu, Yong
Miao, Chunyan
format Conference or Workshop Item
author Wang, Yongjie
Ding, Qinxu
Wang, Ke
Liu, Yue
Wu, Xingyu
Wang, Jinglong
Liu, Yong
Miao, Chunyan
author_sort Wang, Yongjie
title The skyline of counterfactual explanations for machine learning decision models
title_short The skyline of counterfactual explanations for machine learning decision models
title_full The skyline of counterfactual explanations for machine learning decision models
title_fullStr The skyline of counterfactual explanations for machine learning decision models
title_full_unstemmed The skyline of counterfactual explanations for machine learning decision models
title_sort skyline of counterfactual explanations for machine learning decision models
publishDate 2022
url https://hdl.handle.net/10356/156946
_version_ 1772826760688173056