Towards User Guided Actionable Recourse

被引:1
|
作者
Yetukuri, Jayanth [1 ]
Hardy, Ian [1 ]
Liu, Yang [1 ]
机构
[1] Univ Calif Santa Cruz, Santa Cruz, CA 95064 USA
基金
美国国家科学基金会;
关键词
Actionable recourse; User preference;
D O I
10.1145/3600211.3604708
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Machine Learning's proliferation in critical fields such as healthcare, banking, and criminal justice has motivated the creation of tools which ensure trust and transparency in ML models. One such tool is Actionable Recourse (AR) for negatively impacted users. AR describes recommendations of cost-efficient changes to a user's actionable features to help them obtain favorable outcomes. Existing approaches for providing recourse optimize for properties such as proximity, sparsity, validity, and distance-based costs. However, an often-overlooked but crucial requirement for actionability is a consideration of User Preference to guide the recourse generation process. In this work, we attempt to capture user preferences via soft constraints in three simple forms: i) scoring continuous features, ii) bounding feature values and iii) ranking categorical features. Finally, we propose a gradient-based approach to identify User Preferred Actionable Recourse (UP-AR). We carried out extensive experiments to verify the effectiveness of our approach.
引用
下载
收藏
页码:742 / 751
页数:10
相关论文
共 50 条
  • [1] Actionable Recourse in Linear Classification
    Ustun, Berk
    Spangher, Alexander
    Liu, Yang
    FAT*'19: PROCEEDINGS OF THE 2019 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, 2019, : 10 - 19
  • [2] Learning Models for Actionable Recourse
    Ross, Alexis
    Lakkaraju, Himabindu
    Bastani, Osbert
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [3] GAM Coach: Towards Interactive and User-centered Algorithmic Recourse
    Wang, Zijie J.
    Wortman, Jennifer
    Caruana, Rich
    Chau, Duen Horng
    PROCEEDINGS OF THE 2023 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS, CHI 2023, 2023,
  • [4] User Equilibrium with Recourse
    Unnikrishnan, Avinash
    Waller, Steven Travis
    NETWORKS & SPATIAL ECONOMICS, 2009, 9 (04): : 575 - 593
  • [5] User Equilibrium with Recourse
    Avinash Unnikrishnan
    Steven Travis Waller
    Networks and Spatial Economics, 2009, 9 : 575 - 593
  • [6] Individual and Group-level considerations of Actionable Recourse
    Yetukuri, Jayanth
    Liu, Yang
    PROCEEDINGS OF THE 2023 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY, AIES 2023, 2023, : 1008 - 1009
  • [7] CARE: coherent actionable recourse based on sound counterfactual explanations
    Peyman Rasouli
    Ingrid Chieh Yu
    International Journal of Data Science and Analytics, 2024, 17 : 13 - 38
  • [8] CARE: coherent actionable recourse based on sound counterfactual explanations
    Rasouli, Peyman
    Yu, Ingrid Chieh
    INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS, 2024, 17 (01) : 13 - 38
  • [9] Towards Causal Algorithmic Recourse
    Karimi, Amir-Hossein
    von Kuegelgen, Julius
    Schoelkopf, Bernhard
    Valera, Isabel
    XXAI - BEYOND EXPLAINABLE AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers, 2022, 13200 : 139 - 166
  • [10] Counterfactual Explanation Trees: Transparent and Consistent Actionable Recourse with Decision Trees
    Kanamori, Kentaro
    Takagi, Takuya
    Kobayashi, Ken
    Ike, Yuichi
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151