一句话：提出 RUNNER，一步诊断责任不公平神经元并用稳定化重训练修复，显著降低开销并提升 DNN 公平性。
深度神经网络在贷款审批、犯罪风险评估等高风险应用中常表现出对特定群体的歧视，现有公平性改进方法多依赖对抗训练或数据增强，计算开销大；先诊断责任不公平神经元再选择性重训练的方法又因多步样本分析耗时，且间接调整易遇性能瓶颈。本文提出 RUNNER：设计基于重要性的神经元诊断，一步识别责任不公平神经元；提出神经元稳定化重训练，在所有来源中约束不同子群责任不公平神经元的激活距离；并在结构化表格数据与大规模非结构化图像数据上验证泛化性。5个数据集实验表明，RUNNER 将平均计算开销从341.7秒降至29.65秒，公平性最多提升79.3%，同时在非结构化数据集上保持先进结果。
Deep Neural Networks (DNNs), an emerging software technology, have achieved impressive results in a variety of fields. However, the discriminatory behaviors towards certain groups (a.k.a. unfairness) of DNN models increasingly become a social concern, especially in high-stake applications such as loan approval and criminal risk assessment. Although there has been a number of works to improve model fairness, most of them adopt an adversary to either expand the model architecture or augment training data, which introduces excessive computational overhead. Recent work diagnoses responsible unfair neurons first and fixes them with selective retraining. Unfortunately, existing diagnosis process is time-consuming due to multi-step training sample analysis, and selective retraining may cause a performance bottleneck due to indirectly adjusting unfair neurons on biased samples. In this paper, we propose Responsible UNfair NEuron Repair (RUNNER) that improves existing works in three key aspects: (1) efficiency: we design the Importance-based Neuron Diagnosis that identifies responsible unfair neurons in one step with a novel importance criterion of neurons; (2) effectiveness: we design the Neuron Stabilizing Retraining by adding a loss term that measures the activation distance of responsible unfair neurons from different subgroups in all sources; (3) generalization: we investigate the effectiveness on both structured tabular data and large-scale unstructured image data, which is often ignored in prior studies. Our extensive experiments across 5 datasets show that RUUNER can effectively and efficiently diagnose and repair the DNNs regarding unfairness. On average, our approach significantly reduces computing overhead from 341.7s to 29.65s, and achieves improved fairness up to 79.3%. Besides, RUNNER also keeps state-of-the-art results on the unstructured dataset.
@inproceedings{paperbot11248,
title = {RUNNER: Responsible UNfair NEuron Repair for Enhancing Deep Neural Network Fairness},
author = {Tianlin Li and Yue Cao and Jian Zhang and Shiqian Zhao and Yihao Huang and Aishan Liu and Qing Guo and Yang Liu},
booktitle = {ICSE},
year = {2024},
doi = {10.1145/3597503.3623334}
}