Fairness via Group Contribution Matching
Document Type
Conference Proceeding
Publication Date
1-1-2023
Abstract
Fairness issues in Deep Learning models have recently received increasing attention due to their significant societal impact. Although methods for mitigating unfairness are constantly proposed, little research has been conducted to understand how discrimination and bias develop during the standard training process. In this study, we propose analyzing the contribution of each subgroup (i.e., a group of data with the same sensitive attribute) in the training process to understand the cause of such bias development process. We propose a gradient-based metric to assess training subgroup contribution disparity, showing that unequal contributions from different subgroups are one source of such unfairness. One way to balance the contribution of each subgroup is through oversampling, which ensures that an equal number of samples are drawn from each subgroup during each training iteration. However, we find that even with a balanced number of samples, the contribution of each group remains unequal, resulting in unfairness under such a strategy. To address the above issues, we propose an easy but effective group contribution matching (GCM) method to match the contribution of each subgroup. Our experiments show that our GCM effectively improves fairness and outperforms other methods significantly.
Identifier
85170355946 (Scopus)
ISBN
[9781956792034]
Publication Title
Ijcai International Joint Conference on Artificial Intelligence
External Full Text Location
https://doi.org/10.24963/ijcai.2023/49
ISSN
10450823
First Page
436
Last Page
445
Volume
2023-August
Grant
AISG2-RP-2020-019
Fund Ref
National Research Foundation Singapore
Recommended Citation
Li, Tianlin; Li, Zhiming; Li, Anran; Du, Mengnan; Liu, Aishan; Guo, Qing; Meng, Guozhu; and Liu, Yang, "Fairness via Group Contribution Matching" (2023). Faculty Publications. 2382.
https://digitalcommons.njit.edu/fac_pubs/2382