AdFL：浏览器内的联邦学习用于在线广告
AdFL: In-Browser Federated Learning for Online Advertisement
AI总结：
AdFL是一种在浏览器内运行的联邦学习框架，用于学习用户广告偏好，通过聚合全局模型提高广告相关性，同时利用差分隐私保护用户隐私。
摘要：
由于大多数国家正在制定在线隐私法规，例如欧盟的GDPR，在线出版商需要在广告收入和用户隐私之间找到平衡。一种仍然能够根据用户个人和行为信息展示定向广告的方法是采用联邦学习（FL），它在用户之间进行分布式学习而不分享用户原始数据。本文提出了AdFL，一种在浏览器中运行的FL框架，用于学习用户广告偏好。这些偏好在全局FL模型中被聚合，然后用于在浏览器中向用户展示更相关的广告。AdFL可以与任何使用浏览器中可用特征（如广告可见性、广告点击率、用户在页面上的停留时间、页面内容）的模型一起工作。AdFL服务器位于出版商处，并协调浏览出版商网站页面的用户的 学习过程。AdFL原型不需要客户端安装任何软件，因为它利用了大多数现代浏览器中可用的标准API。我们为广告可见性预测构建了一个概念验证模型，该模型建立在AdFL之上。我们使用两个非重叠的数据集测试了AdFL和该模型，这些数据集来自每天有40,000名访客的网站。实验表明，AdFL能够在几毫秒内捕获浏览器中的训练信息，证明广告可见性预测达到92.59%的AUC，并表明使用差分隐私（DP）来保护本地模型参数可以实现足够的性能，与非DP变体相比只有适度的性能下降。
英文摘要：
Since most countries are coming up with online privacy regulations, such as GDPR in the EU, online publishers need to find a balance between revenue from targeted advertisement and user privacy. One way to be able to still show targeted ads, based on user personal and behavioral information, is to employ Federated Learning (FL), which performs distributed learning across users without sharing user raw data with other stakeholders in the publishing ecosystem. This paper presents AdFL, an FL framework that works in the browsers to learn user ad preferences. These preferences are aggregated in a global FL model, which is then used in the browsers to show more relevant ads to users. AdFL can work with any model that uses features available in the browser such as ad viewability, ad click-through, user dwell time on pages, and page content. The AdFL server runs at the publisher and coordinates the learning process for the users who browse pages on the publisher's website. The AdFL prototype does not require the client to install any software, as it is built utilizing standard APIs available on most modern browsers. We built a proof-of-concept model for ad viewability prediction that runs on top of AdFL. We tested AdFL and the model with two non-overlapping datasets from a website with 40K visitors per day. The experiments demonstrate AdFL's feasibility to capture the training information in the browser in a few milliseconds, show that the ad viewability prediction achieves up to 92.59% AUC, and indicate that utilizing differential privacy (DP) to safeguard local model parameters yields adequate performance, with only modest declines in comparison to the non-DP variant.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
