@inproceedings{e7e114dc170446da83fc1480f5e7a392,
title = "AIM: Attributing, Interpreting, Mitigating Data Unfairness",
abstract = "Data collected in the real world often encapsulates historical discrimination against disadvantaged groups and individuals. Existing fair machine learning (FairML) research has predominantly focused on mitigating discriminative bias in the model prediction, with far less effort dedicated towards exploring how to trace biases present in the data, despite its importance for the transparency and interpretability of FairML. To fill this gap, we investigate a novel research problem: discovering samples that reflect biases/prejudices from the training data. Grounding on the existing fairness notions, we lay out a sample bias criterion and propose practical algorithms for measuring and countering sample bias. The derived bias score provides intuitive sample-level attribution and explanation of historical bias in data. On this basis, we further design two FairML strategies via sample-bias-informed minimal data editing. They can mitigate both group and individual unfairness at the cost of minimal or zero predictive utility loss. Extensive experiments and analyses on multiple real-world datasets demonstrate the effectiveness of our methods in explaining and mitigating unfairness. Code is available at https://github.com/ZhiningLiu1998/AIM.",
keywords = "bias attribution, fairml, group fairness, individual fairness",
author = "Zhining Liu and Ruizhong Qiu and Zhichen Zeng and Yada Zhu and Hendrik Hamann and Hanghang Tong",
note = "This work is supported by NSF (1939725), AFOSR (FA9550-24-1- 0002), the C3.ai Digital Transformation Institute, MIT-IBM Watson AI Lab, and IBM-Illinois Discovery Accelerator Institute. The content of the information in this document does not necessarily reflect the position or the policy of the Government, and no official endorsement should be inferred. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.; 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024 ; Conference date: 25-08-2024 Through 29-08-2024",
year = "2024",
month = aug,
day = "24",
doi = "10.1145/3637528.3671797",
language = "English (US)",
series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery",
pages = "2014--2025",
booktitle = "KDD 2024 - Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining",
address = "United States",
}