当前位置: X-MOL 学术arXiv.cs.IR › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Privacy-Preserving News Recommendation Model Learning
arXiv - CS - Information Retrieval Pub Date : 2020-03-21 , DOI: arxiv-2003.09592
Tao Qi, Fangzhao Wu, Chuhan Wu, Yongfeng Huang, Xing Xie

News recommendation aims to display news articles to users based on their personal interest. Existing news recommendation methods rely on centralized storage of user behavior data for model training, which may lead to privacy concerns and risks due to the privacy-sensitive nature of user behaviors. In this paper, we propose a privacy-preserving method for news recommendation model training based on federated learning, where the user behavior data is locally stored on user devices. Our method can leverage the useful information in the behaviors of massive number users to train accurate news recommendation models and meanwhile remove the need of centralized storage of them. More specifically, on each user device we keep a local copy of the news recommendation model, and compute gradients of the local model based on the user behaviors in this device. The local gradients from a group of randomly selected users are uploaded to server, which are further aggregated to update the global model in the server. Since the model gradients may contain some implicit private information, we apply local differential privacy (LDP) to them before uploading for better privacy protection. The updated global model is then distributed to each user device for local model update. We repeat this process for multiple rounds. Extensive experiments on a real-world dataset show the effectiveness of our method in news recommendation model training with privacy protection.

中文翻译:

隐私保护新闻推荐模型学习

新闻推荐旨在根据用户的个人兴趣向用户展示新闻文章。现有的新闻推荐方法依赖于用户行为数据的集中存储进行模型训练,由于用户行为的隐私敏感性,这可能会导致隐私问题和风险。在本文中,我们提出了一种基于联邦学习的新闻推荐模型训练隐私保护方法,其中用户行为数据本地存储在用户设备上。我们的方法可以利用海量用户行为中的有用信息来训练准确的新闻推荐模型,同时消除对它们的集中存储的需要。更具体地说,在每个用户设备上,我们保留新闻推荐模型的本地副本,并根据该设备中的用户行为计算本地模型的梯度。来自一组随机选择的用户的局部梯度被上传到服务器,这些梯度被进一步聚合以更新服务器中的全局模型。由于模型梯度可能包含一些隐含的隐私信息,我们在上传之前对其应用局部差分隐私(LDP)以更好地保护隐私。然后将更新的全局模型分发到每个用户设备以进行本地模型更新。我们重复这个过程多轮。对真实世界数据集的大量实验表明,我们的方法在具有隐私保护的新闻推荐模型训练中是有效的。我们在上传之前对其应用本地差分隐私(LDP)以更好地保护隐私。然后将更新的全局模型分发到每个用户设备以进行本地模型更新。我们重复这个过程多轮。对真实世界数据集的大量实验表明,我们的方法在具有隐私保护的新闻推荐模型训练中是有效的。我们在上传之前对其应用本地差分隐私(LDP)以更好地保护隐私。然后将更新的全局模型分发到每个用户设备以进行本地模型更新。我们重复这个过程多轮。对真实世界数据集的大量实验表明,我们的方法在具有隐私保护的新闻推荐模型训练中是有效的。
更新日期:2020-10-09
down
wechat
bug