ICSE 2024
Fri 12 - Sun 21 April 2024 Lisbon, Portugal
Thu 18 Apr 2024 15:30 - 16:00 at Open Space - Posters 4

Although several fairness definitions and bias mitigation techniques exist in the literature, all existing solutions evaluate fairness of Machine Learning (ML) systems after the training stage. In this paper, we take the first steps towards evaluating a more holistic approach by testing for fairness both before and after model training. We evaluate the effectiveness of the proposed approach and position it within the ML development lifecycle, using an empirical analysis of the relationship between model dependent and independent fairness metrics. The study uses 2 fairness metrics, 4 ML algorithms, 5 real-world datasets and 1600 fairness evaluation cycles. We find a linear relationship between data and model fairness metrics when the distribution and the size of the training data changes. Our results indicate that testing for fairness prior to training can be a ``cheap'' and effective means of catching a biased data collection process early; detecting data drifts in production systems and minimising execution of full training cycles thus reducing development time and costs.

Thu 18 Apr

Displayed time zone: Lisbon change

15:30 - 16:00
Posters 4Posters at Open Space
15:30
30m
Poster
Towards Data Augmentation for Supervised Code Translation
Posters
Binger Chen Technische Universität Berlin, Jacek golebiowski Amazon AWS, Ziawasch Abedjan Leibniz Universität Hannover
15:30
30m
Poster
GDPR indications in commits messages in GitHub repositories
Posters
Georgia Kapitsaki University of Cyprus, Maria Papoutsoglou University of Cyprus
15:30
30m
Poster
Automatic Generation of Test Cases based on Bug Reports: a Feasibility Study with Large Language Models
Posters
Laura Plein University of Luxembourg, Wendkuuni Arzouma Marc Christian OUEDRAOGO University of Luxembourg, Jacques Klein University of Luxembourg, Tegawendé F. Bissyandé University of Luxembourg
15:30
30m
Poster
How Does Pre-trained Language Model Perform on Deep Learning Framework Bug Prediction?
Posters
Xiaoting Du Beijing University of Posts and Telecommunications, Chenglong Li Beihang University, Xiangyue Ma Beihang University, Zheng Zheng Beihang University
15:30
30m
Poster
xNose: A Test Smell Detector for C#
Posters
Partha Protim Paul Shahjalal University of Science & Technology, Md Tonoy Akanda Shahjalal University of Science & Technology, Mohammed Raihan Ullah Shahjalal University of Science & Technology, Dipto Mondal Shahjalal University of Science & Technology, Nazia Sultana Chowdhury Shahjalal University of Science & Technology, Fazle Mohammed Tawsif University of Southern California
DOI Pre-print
15:30
30m
Poster
Data vs. Model Machine Learning Fairness Testing: An Empirical Study
Posters
Arumoy Shome Delft University of Technology, Luís Cruz Delft University of Technology, Arie van Deursen Delft University of Technology
15:30
30m
Poster
On the Effects of Program Slicing for Vulnerability Detection during Code Inspection: Extended Abstract
Posters
Aurora Papotti Vrije Universiteit Amsterdam, Fabio Massacci University of Trento; Vrije Universiteit Amsterdam, Katja Tuma Vrije Universiteit Amsterdam
15:30
30m
Poster
Multi-step Automated Generation of Parameter Docstrings in Python: An Exploratory Study
Posters
Vatsal Venkatkrishna Australian National University, Durga Shree Nagabushanam Australian National University, Emmanuel Iko-Ojo Simon Australian National University, Melina Vidoni Australian National University
DOI Authorizer link
15:30
30m
Poster
Lightweight Semantic Conflict Detection with Static Analysis
Posters
Galileu Santos de Jesus Federal University of Pernambuco, Paulo Borba Federal University of Pernambuco, Rodrigo Bonifácio Computer Science Department - University of Brasília, Matheus Barbosa de Oliveira Federal University of Pernambuco
15:30
30m
Poster
Energy Consumption of Automated Program Repair
Posters
Matias Martinez Universitat Politècnica de Catalunya (UPC), Silverio Martínez-Fernández UPC-BarcelonaTech, Xavier Franch Universitat Politècnica de Catalunya
15:30
30m
Poster
ReviewRanker: A Semi-Supervised Learning Based Approach for Code Review Quality Estimation
Posters
Saifullah Mahbub United International University, Md. Easin Arafat Eötvös Loránd University, Chowdhury Rafeed Rahman National University of Singapore, Zannatul Ferdows United International University, Masum Hasan University of Rochester
15:30
30m
Poster
LogPrompt: Prompt Engineering Towards Zero-Shot and Interpretable Log Analysis
Posters
Yilun Liu Huawei co. LTD, Shimin Tao University of Science and Technology of China; Huawei co. LTD, Weibin Meng Huawei co. LTD, Feiyu Yao Huawei co. LTD, Xiaofeng Zhao Huawei co. LTD, Hao Yang Huawei co. LTD
15:30
30m
Poster
High-precision Online Log Parsing with Large Language Models
Posters
XiaoLei Chen Fudan University, Jie Shi Fudan University, ChenJ , Peng Wang Fudan University, Wei Wang Fudan University
15:30
30m
Poster
Multi-requirement Parametric Falsification
Posters
Matteo Camilli Politecnico di Milano, Raffaela Mirandola Karlsruhe Institute of Technology (KIT)