Write a Blog >>
ESEC/FSE 2021
Mon 23 - Sat 28 August 2021 Athens, Greece

This program is tentative and subject to change.

Wed 25 Aug 2021 16:30 - 16:45 - AI—Software Engineering for Machine Learning 2
Thu 26 Aug 2021 04:30 - 04:45 - AI—Software Engineering for Machine Learning 2

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.

This program is tentative and subject to change.

Conference Day
Wed 25 Aug

Displayed time zone: Athens change

16:00 - 17:00
AI—Software Engineering for Machine Learning 2Journal First / Research Papers / Ideas, Visions and Reflections +12h
16:00
15m
Talk
Selecting Test Inputs for DNNs using Differential Testing with Subspecialized Model Instances
Ideas, Visions and Reflections
Yu-Seung MaElectronics and Telecommunications Research Institute, Shin YooKorea Advanced Institute of Science and Technology, Taeho KimElectronics and Telecommunications Research Institute (ETRI)
16:15
15m
Talk
Fairea: A Model Behaviour Mutation Approach to Benchmarking Bias Mitigation Methods
Research Papers
Max HortUniversity College London, Jie M. ZhangUniversity College London, UK, Federica SarroUniversity College London, Mark HarmanUniversity College London
16:30
15m
Talk
Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline
Research Papers
Sumon BiswasIowa State University, USA, Hridesh RajanIowa State University, USA
DOI Pre-print Media Attached
16:45
15m
Talk
The Current State of Industrial Practice in Artificial Intelligence Ethics
Journal First
Ville VakkuriUniversity of Jyvaskyla, Kai-Kristian KemellUniversity of Jyvaskyla, Joni KultanenUniversity of Jyvaskyla, Pekka AbrahamssonUniversity of Jyväskylä

Conference Day
Thu 26 Aug

Displayed time zone: Athens change

04:00 - 05:00
AI—Software Engineering for Machine Learning 2Research Papers / Ideas, Visions and Reflections / Journal First
04:00
15m
Talk
Selecting Test Inputs for DNNs using Differential Testing with Subspecialized Model Instances
Ideas, Visions and Reflections
Yu-Seung MaElectronics and Telecommunications Research Institute, Shin YooKorea Advanced Institute of Science and Technology, Taeho KimElectronics and Telecommunications Research Institute (ETRI)
04:15
15m
Talk
Fairea: A Model Behaviour Mutation Approach to Benchmarking Bias Mitigation Methods
Research Papers
Max HortUniversity College London, Jie M. ZhangUniversity College London, UK, Federica SarroUniversity College London, Mark HarmanUniversity College London
04:30
15m
Talk
Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline
Research Papers
Sumon BiswasIowa State University, USA, Hridesh RajanIowa State University, USA
DOI Pre-print Media Attached
04:45
15m
Talk
The Current State of Industrial Practice in Artificial Intelligence Ethics
Journal First
Ville VakkuriUniversity of Jyvaskyla, Kai-Kristian KemellUniversity of Jyvaskyla, Joni KultanenUniversity of Jyvaskyla, Pekka AbrahamssonUniversity of Jyväskylä