一句话：提出 NeuFair，通过推理期随机丢弃神经元对预训练 DNN 进行后处理公平性修复，同时尽量保持模型效用。
深度神经网络在关键社会领域广泛应用，但可能编码并放大历史偏见；现有公平性缓解方法常需修改数据集或学习算法。论文研究将神经元 dropout 作为预训练 DNN 的后处理偏差缓解手段，提出 NeuFair：一族在推理阶段通过随机丢弃神经元来降低不公平性的后处理随机算法。由于寻找最优丢弃神经元集合是组合问题，NeuFair 以最小化歧视并保持模型效用为目标进行随机搜索。实验表明该方法高效且有效，公平性最高提升 69%，模型性能几乎或完全不下降；作者还解释该现象并分析超参数影响，最后与多种最先进偏差缓解器进行实证与概念比较。
This paper investigates neuron dropout as a post-processing bias mitigation method for deep neural networks (DNNs). Neural-driven software solutions are increasingly applied in socially critical domains with significant fairness implications. While DNNs are exceptional at learning statistical patterns from data, they may encode and amplify historical biases. Existing bias mitigation algorithms often require modifying the input dataset or the learning algorithms. We posit that prevalent dropout methods may be an effective and less intrusive approach to improve fairness of pre-trained DNNs during inference. However, finding the ideal set of neurons to drop is a combinatorial problem. We propose NeuFair, a family of post-processing randomized algorithms that mitigate unfairness in pre-trained DNNs via dropouts during inference. Our randomized search is guided by an objective to minimize discrimination while maintaining the model’s utility. We show that NeuFair is efficient and effective in improving fairness (up to 69%) with minimal or no model performance degradation. We provide intuitive explanations of these phenomena and carefully examine the influence of various hyperparameters of NeuFair on the results. Finally, we empirically and conceptually compare NeuFair to different state-of-the-art bias mitigators.
DOI 原文 ·
@inproceedings{paperbot8482,
title = {NeuFair: Neural Network Fairness Repair with Dropout},
author = {Vishnu Asutosh Dasu and Ashish Kumar and Saeid Tizpaz-Niari and Gang Tan},
booktitle = {ISSTA},
year = {2024},
doi = {10.1145/3650212.3680380}
}