The Importance of Time in Causal Algorithmic Recourse

被引:1
|
作者
Beretta, Isacco [1 ]
Cinquini, Martina [1 ]
机构
[1] Univ Pisa, Pisa, Italy
基金
欧盟地平线“2020”;
关键词
Algorithmic Recourse; Causality; Consequential Recommendations;
D O I
10.1007/978-3-031-44064-9_16
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The application of Algorithmic Recourse in decision-making is a promising field that offers practical solutions to reverse unfavorable decisions. However, the inability of these methods to consider potential dependencies among variables poses a significant challenge due to the assumption of feature independence. Recent advancements have incorporated knowledge of causal dependencies, thereby enhancing the quality of the recommended recourse actions. Despite these improvements, the inability to incorporate the temporal dimension remains a significant limitation of these approaches. This is particularly problematic as identifying and addressing the root causes of undesired outcomes requires understanding time-dependent relationships between variables. In this work, we motivate the need to integrate the temporal dimension into causal algorithmic recourse methods to enhance recommendations' plausibility and reliability. The experimental evaluation highlights the significance of the role of time in this field.
引用
收藏
页码:283 / 298
页数:16
相关论文
共 50 条
  • [1] Towards Causal Algorithmic Recourse
    Karimi, Amir-Hossein
    von Kuegelgen, Julius
    Schoelkopf, Bernhard
    Valera, Isabel
    [J]. 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
  • [2] On the Fairness of Causal Algorithmic Recourse
    von Kuegelgen, Julius
    Karimi, Amir-Hossein
    Bhatt, Umang
    Valera, Isabel
    Weller, Adrian
    Schoelkopf, Bernhard
    [J]. THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 9584 - 9594
  • [3] On the Adversarial Robustness of Causal Algorithmic Recourse
    Dominguez-Olmedo, Ricardo
    Karimi, Amir-Hossein
    Schoelkopf, Bernhard
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [4] Robustness Implies Fairness in Causal Algorithmic Recourse
    Ehyaei, Ahmad-Reza
    Karimi, Amir-Hossein
    Schoelkopf, Bernhard
    Maghsudi, Setareh
    [J]. PROCEEDINGS OF THE 6TH ACM CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, FACCT 2023, 2023, : 984 - 1001
  • [5] The Game Of Recourse: Simulating Algorithmic Recourse over Time to Improve Its Reliability and Fairness
    Bell, Andrew
    Fonseca, Joao
    Stoyanovich, Julia
    [J]. COMPANION OF THE 2024 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, SIGMOD-COMPANION 2024, 2024, : 464 - 467
  • [6] Setting the Right Expectations: Algorithmic Recourse Over Time
    Fonseca, Joao
    Bell, Andrew
    Abrate, Carlo
    Bonchi, Francesco
    Stoyanovich, Julia
    [J]. PROCEEDINGS OF 2023 ACM CONFERENCE ON EQUITY AND ACCESS IN ALGORITHMS, MECHANISMS, AND OPTIMIZATION, EAAMO 2023, 2023,
  • [7] The philosophical basis of algorithmic recourse
    Venkatasubramanian, Suresh
    Alfano, Mark
    [J]. FAT* '20: PROCEEDINGS OF THE 2020 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, 2020, : 284 - 293
  • [8] Algorithmic Recourse in Mental Healthcare
    Lacerda, Anisio
    Almeida, Claudio
    Ferreira, Leonardo
    Pereira, Adriano
    Pappa, Gisele L.
    Meira, Wagner, Jr.
    Miranda, Debora
    Romano-Silva, Marco A.
    Diniz, Leandro Malloy
    [J]. 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [9] Bayesian Persuasion for Algorithmic Recourse
    Harris, Keegan
    Chen, Valerie
    Kim, Joon Sik
    Talwalkar, Ameet
    Heidari, Hoda
    Wu, Zhiwei Steven
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [10] Endogenous Macrodynamics in Algorithmic Recourse
    Altmeyer, Patrick
    Angela, Giovan
    Buszydlik, Aleksander
    Dobiczek, Karol
    van Deursen, Arie
    Liem, Cynthia C. S.
    [J]. 2023 IEEE CONFERENCE ON SECURE AND TRUSTWORTHY MACHINE LEARNING, SATML, 2023, : 418 - 431