TY - GEN
T1 - FairPrep
T2 - 23rd International Conference on Extending Database Technology, EDBT 2020
AU - Schelter, Sebastian
AU - He, Yuxuan
AU - Khilnani, Jatin
AU - Stoyanovich, Julia
N1 - Publisher Copyright:
© 2020 Copyright held by the owner/author(s). Published in Proceedings of the 23rd International Conference on Extending Database Technology (EDBT), March 30-April 2, 2020, ISBN 978-3-89318-083-7 on OpenProceedings.org. Distribution of this paper is permitted under the terms of the Creative Commons license CC-by-nc-nd 4.0.
PY - 2020
Y1 - 2020
N2 - The importance of incorporating ethics and legal compliance into machine-assisted decision-making is broadly recognized. Further, several lines of recent work have argued that critical opportunities for improving data quality and representativeness, controlling for bias, and allowing humans to oversee and impact computational processes are missed if we do not consider the lifecycle stages upstream from model training and deployment. Yet, very little has been done to date to provide system-level support to data scientists who wish to develop responsible machine learning methods. We aim to fill this gap and present FairPrep, a design and evaluation framework for fairness-enhancing interventions, which helps data scientists follow best practices in ML experimentation. We identify shortcomings in existing empirical studies for analyzing fairness-enhancing interventions and show how FairPrep can be used to measure their impact. Our results suggest that the high variability of the outcomes of fairness-enhancing interventions observed in previous studies is often an artifact of a lack of hyperparameter tuning, and that the choice of a data cleaning method can impact the effectiveness of fairness-enhancing interventions.
AB - The importance of incorporating ethics and legal compliance into machine-assisted decision-making is broadly recognized. Further, several lines of recent work have argued that critical opportunities for improving data quality and representativeness, controlling for bias, and allowing humans to oversee and impact computational processes are missed if we do not consider the lifecycle stages upstream from model training and deployment. Yet, very little has been done to date to provide system-level support to data scientists who wish to develop responsible machine learning methods. We aim to fill this gap and present FairPrep, a design and evaluation framework for fairness-enhancing interventions, which helps data scientists follow best practices in ML experimentation. We identify shortcomings in existing empirical studies for analyzing fairness-enhancing interventions and show how FairPrep can be used to measure their impact. Our results suggest that the high variability of the outcomes of fairness-enhancing interventions observed in previous studies is often an artifact of a lack of hyperparameter tuning, and that the choice of a data cleaning method can impact the effectiveness of fairness-enhancing interventions.
UR - http://www.scopus.com/inward/record.url?scp=85084183336&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85084183336&partnerID=8YFLogxK
U2 - 10.5441/002/edbt.2020.41
DO - 10.5441/002/edbt.2020.41
M3 - Conference contribution
AN - SCOPUS:85084183336
T3 - Advances in Database Technology - EDBT
SP - 395
EP - 398
BT - Advances in Database Technology - EDBT 2020
A2 - Bonifati, Angela
A2 - Zhou, Yongluan
A2 - Vaz Salles, Marcos Antonio
A2 - Bohm, Alexander
A2 - Olteanu, Dan
A2 - Fletcher, George
A2 - Khan, Arijit
A2 - Yang, Bin
PB - OpenProceedings.org
Y2 - 30 March 2020 through 2 April 2020
ER -