Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline

被引:49
|
作者
Biswas, Sumon [1 ]
Rajan, Hridesh [1 ]
机构
[1] Iowa State Univ, Dept Comp Sci, Ames, IA 50011 USA
来源
PROCEEDINGS OF THE 29TH ACM JOINT MEETING ON EUROPEAN SOFTWARE ENGINEERING CONFERENCE AND SYMPOSIUM ON THE FOUNDATIONS OF SOFTWARE ENGINEERING (ESEC/FSE '21) | 2021年
关键词
fairness; machine learning; preprocessing; pipeline; models; IMPACT;
D O I
10.1145/3468264.3468536
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
In recent years, many incidents have been reported where machine learning models exhibited discrimination among people based on race, sex, age, etc. Research has been conducted to measure and mitigate unfairness in machine learning models. For a machine learning task, it is a common practice to build a pipeline that includes an ordered set of data preprocessing stages followed by a classifier. However, most of the research on fairness has considered a single classifier based prediction task. What are the fairness impacts of the preprocessing stages in machine learning pipeline? Furthermore, studies showed that often the root cause of unfairness is ingrained in the data itself, rather than the model. But no research has been conducted to measure the unfairness caused by a specific transformation made in the data preprocessing stage. In this paper, we introduced the causal method of fairness to reason about the fairness impact of data preprocessing stages in ML pipeline. We leveraged existing metrics to define the fairness measures of the stages. Then we conducted a detailed fairness evaluation of the preprocessing stages in 37 pipelines collected from three different sources. Our results show that certain data transformers are causing the model to exhibit unfairness. We identified a number of fairness patterns in several categories of data transformers. Finally, we showed how the local fairness of a preprocessing stage composes in the global fairness of the pipeline. We used the fairness composition to choose appropriate downstream transformer that mitigates unfairness in the machine learning pipeline.
引用
收藏
页码:981 / 993
页数:13
相关论文
共 50 条
  • [1] Towards Explaining the Effects of Data Preprocessing on Machine Learning
    Zelaya, Carlos Vladimiro Gonzalez
    2019 IEEE 35TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2019), 2019, : 2086 - 2090
  • [2] Microbiome Preprocessing Machine Learning Pipeline
    Jasner, Yoel Y.
    Belogolovski, Anna
    Ben-Itzhak, Meirav
    Koren, Omry
    Louzoun, Yoram
    FRONTIERS IN IMMUNOLOGY, 2021, 12
  • [3] Towards Understanding Fairness and its Composition in Ensemble Machine Learning
    Gohar, Usman
    Biswas, Sumon
    Rajan, Hridesh
    2023 IEEE/ACM 45TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, ICSE, 2023, : 1533 - 1545
  • [4] Towards FAIR Data in Distributed Machine Learning Systems
    Mou, Yongli
    Guo, Fengyang
    Lu, Wei
    Li, Yongzhao
    Beyan, Oya
    Rose, Thomas
    Dustdar, Schahram
    Decker, Stefan
    IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM, 2023, : 6450 - 6455
  • [5] A Data-Driven Methodology for Guiding the Selection of Preprocessing Techniques in a Machine Learning Pipeline
    Garcia-Carraseo, Jorge
    Mate, Alejandro
    Trujillo, Juan
    INTELLIGENT INFORMATION SYSTEMS, CAISE FORUM 2023, 2023, 477 : 34 - 42
  • [6] On Learning and Testing of Counterfactual Fairness through Data Preprocessing
    Chen, Haoyu
    Lu, Wenbin
    Song, Rui
    Ghosh, Pulak
    JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2024, 119 (546) : 1286 - 1296
  • [7] Strategic Best Response Fairness in Fair Machine Learning
    Shimao, Hajime
    Khern-am-nuai, Warut
    Kannan, Karthik
    Cohen, Maxime C.
    PROCEEDINGS OF THE 2022 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY, AIES 2022, 2022, : 664 - 664
  • [8] FAIR Machine Learning Model Pipeline Implementation of COVID-19 Data
    Folorunso, Sakinat
    Ogundepo, Ezekiel
    Basajja, Mariam
    Awotunde, Joseph
    Kawu, Abdullahi
    Oladipo, Francisca
    Ibrahim, Abdullahi
    DATA INTELLIGENCE, 2022, 4 (04) : 971 - 990
  • [9] FAIR Machine Learning Model Pipeline Implementation of COVID-19 Data
    Sakinat Folorunso
    Ezekiel Ogundepo
    Mariam Basajja
    Joseph Awotunde
    Abdullahi Kawu
    Francisca Oladipo
    Abdullahi Ibrahim
    Data Intelligence, 2022, 4 (04) : 971 - 990
  • [10] FAIR Machine Learning Model Pipeline Implementation of COVID-19 Data
    Folorunso, Sakinat
    Ogundepo, Ezekiel
    Basajja, Mariam
    Awotunde, Joseph
    Kawu, Abdullahi
    Oladipo, Francisca
    Abdullahi, Ibrahim
    Data Intelligence, 2022, 4