Assessing Unfairness in GNN-Based Recommender Systems: A Focus on Metrics for Demographic Sub-Groups

Nikzad Chizari, Keywan Tajfar, María N. Moreno-García

2024

Abstract

Recommender Systems (RS) have become a central tool for providing personalized suggestions, yet the growing complexity of modern methods, such as Graph Neural Networks (GNNs), has introduced new challenges related to bias and fairness. While these methods excel at capturing intricate relationships between users and items, they often amplify biases present in the data, leading to discriminatory outcomes especially against protected demographic groups like gender and age. This study evaluates and measures fairness in GNN-based RS by investigating the extent of unfairness towards various groups and su bgroups within these systems. By employing performance metrics like NDCG, this research highlights disparities in recommendation quality across different demographic groups, emphasizing the importance of accurate, group-level measurement. This analysis not only sheds light on how these biases manifest but also lays the groundwork for developing more equitable recommendation systems that ensure fair treatment across all user groups.

Paper Citation

in Harvard Style

Chizari N., Tajfar K. and N. Moreno-García M. (2024). Assessing Unfairness in GNN-Based Recommender Systems: A Focus on Metrics for Demographic Sub-Groups. In Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST; ISBN 978-989-758-718-4, SciTePress, pages 433-440. DOI: 10.5220/0013069400003825

in Bibtex Style

@conference{webist24,
author={Nikzad Chizari and Keywan Tajfar and María N. Moreno-García},
title={Assessing Unfairness in GNN-Based Recommender Systems: A Focus on Metrics for Demographic Sub-Groups},
booktitle={Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST},
year={2024},
pages={433-440},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013069400003825},
isbn={978-989-758-718-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST
TI - Assessing Unfairness in GNN-Based Recommender Systems: A Focus on Metrics for Demographic Sub-Groups
SN - 978-989-758-718-4
AU - Chizari N.
AU - Tajfar K.
AU - N. Moreno-García M.
PY - 2024
SP - 433
EP - 440
DO - 10.5220/0013069400003825
PB - SciTePress