Socially Responsible Machine Learning: A Causal Perspective

被引:0
|
作者
Moraffah, Raha [1 ]
Karimi, Amir-Hossein [2 ]
Raglin, Adrienne [3 ]
Liu, Huan [1 ]
机构
[1] Arizona State Univ, Tempe, AZ 85281 USA
[2] Max Planck Inst Intelligent Syst, Tubingen, Germany
[3] Army Res Lab, Baltimore, MD USA
关键词
Responsible ML; Causality; Fairness; Interpretability; Robustness;
D O I
10.1145/3580305.3599571
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The evergrowing reliance of humans and society on machine learning methods has raised concerns about their trustworthiness and liability. As a response to these concerns, Socially Responsible Machine Learning (SRML) aims at developing fair, transparent, and robust machine learning algorithms. However, traditional approaches to SRML do not incorporate human perspectives, and therefore are not sufficient to build long-lasting trust between machines and human being. Causality as the key to human intelligence plays a vital role in achieving socially responsible machine learning algorithms which are compatible with human notions. Bridging the gap between traditional SRML and causality, in this tutorial, we aim at providing a holistic overview of SRML through the lens of causality. In particular, we will focus on state-of-the-art techniques on causal socially responsible ML in terms of fairness, interpretability, and robustness. The objectives of this tutorial are as follows: (1) we provide a taxonomy of existing literature on causal socially responsible ML from fairness, interpretability, and robustness perspective; (2) we review the state-of-the-art techniques for each task; and (3) we elucidate open questions and future research directions. We believe this tutorial is beneficial to researchers and practitioners from the areas of data mining, machine learning, and social sciences.
引用
收藏
页码:5819 / 5820
页数:2
相关论文
共 50 条
  • [1] Causal Learning for Socially Responsible AI
    Cheng, Lu
    Mosallanezhad, Ahmadreza
    Sheth, Paras
    Liu, Huan
    [J]. PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 4374 - 4381
  • [2] A machine learning perspective on responsible gambling
    Hassanniakalager, Arman
    Newall, Philip W. S.
    [J]. BEHAVIOURAL PUBLIC POLICY, 2022, 6 (02) : 237 - 260
  • [3] Socially Responsible Investing: An Investor Perspective
    Thomas C. Berry
    Joan C. Junkus
    [J]. Journal of Business Ethics, 2013, 112 : 707 - 720
  • [4] Socially Responsible Investing: An Investor Perspective
    Berry, Thomas C.
    Junkus, Joan C.
    [J]. JOURNAL OF BUSINESS ETHICS, 2013, 112 (04) : 707 - 720
  • [5] A causal perspective on dataset bias in machine learning for medical imaging
    Jones, Charles
    Castro, Daniel C.
    Ribeiro, Fabio De Sousa
    Oktay, Ozan
    Mccradden, Melissa
    Glocker, Ben
    [J]. NATURE MACHINE INTELLIGENCE, 2024, 6 (02) : 138 - 146
  • [6] A causal perspective on dataset bias in machine learning for medical imaging
    Charles Jones
    Daniel C. Castro
    Fabio De Sousa Ribeiro
    Ozan Oktay
    Melissa McCradden
    Ben Glocker
    [J]. Nature Machine Intelligence, 2024, 6 : 138 - 146
  • [7] Organizational learning as a tool for the University socially responsible
    Henriquez Fuentes, Gustavo Rafael
    Vallaeys, Francois
    Garzon Castrillon, Manuel Alfonso
    [J]. REVISTA PENSAMIENTO AMERICANO, 2018, 11 (20): : 116 - 140
  • [8] DEVELOPMENT OF SUSTAINABLE AND SOCIALLY RESPONSIBLE BUSINESS: A STAKEHOLDER PERSPECTIVE
    Susniene, Dalia
    Sargunas, Gediminas
    [J]. CHANGES IN SOCIAL AND BUSINESS ENVIRONMENT (CISABE'13), 2013, : 163 - 169
  • [9] On the neutrality of socially responsible investing: The general equilibrium perspective
    Arnold, Lutz G. G.
    [J]. THEORETICAL ECONOMICS, 2023, 18 (01) : 65 - 95
  • [10] Principles for a Socially Responsible Lexicography from a Glotopolitical Perspective
    Rodriguez Barcia, Susana
    [J]. QUADERNS DE FILOLOGIA-ESTUDIS LINGUISTICS, 2023, 28 : 37 - 54