差别隐私
协同过滤
计算机科学
随机梯度下降算法
推荐系统
机器学习
人工智能
数据挖掘
人工神经网络
作者
Zhenhuan Yang,Yingqiang Ge,Congzhe Su,Dingxian Wang,Xiaoting Zhao,Yiming Ying
出处
期刊:
[Association for Computing Machinery]
日期:2023-04-28
卷期号:: 927-931
被引量:13
标识
DOI:10.1145/3543873.3587577
摘要
Recently, there has been an increasing adoption of differential privacy guided algorithms for privacy-preserving machine learning tasks. However, the use of such algorithms comes with trade-offs in terms of algorithmic fairness, which has been widely acknowledged. Specifically, we have empirically observed that the classical collaborative filtering method, trained by differentially private stochastic gradient descent (DP-SGD), results in a disparate impact on user groups with respect to different user engagement levels. This, in turn, causes the original unfair model to become even more biased against inactive users. To address the above issues, we propose DP-Fair, a two-stage framework for collaborative filtering based algorithms. Specifically, it combines differential privacy mechanisms with fairness constraints to protect user privacy while ensuring fair recommendations. The experimental results, based on Amazon datasets, and user history logs collected from Etsy, one of the largest e-commerce platforms, demonstrate that our proposed method exhibits superior performance in terms of both overall accuracy and user group fairness on both shallow and deep recommendation models compared to vanilla DP-SGD.
科研通智能强力驱动
Strongly Powered by AbleSci AI