A scalable privacy-preserving information retrieval system based on federated optimization, on-device intelligence and semantic matching

基于联合优化、设备端智能和语义匹配的可扩展隐私保护信息检索系统

• 批准号: 19H04215
• 负责人: 于 海涛
• 金额: $ 10.15万
• 依托单位: University of Tsukuba
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 2019
• 资助国家: 日本
• 起止时间: 2019-04-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-19H04215/
• 关键词: privacy-preserving; federated learning; semantic matching; online learning-to-rank; interactive search; on-device learning; Metric Optimization; Policy Gradient; Differential Privacy; Privacy-preserving IR; Federated Optimization; On-device Lea

This year our main task is to develop the federated information retrieval model based on a large-scale dataset. To this end, we firstly view information retrieval as an interactive process between users and the search engine system rather than an independent ranking per query. Secondly, we explore how to effectively integrate online learning-to-rank and federated learning. Specifically, online learning-to-rank enables us to cope with the aforementioned interactive process. Federated learning enables us to deal with the privacy issue by learning the ranking model in an on-device manner. Based on a series of experiments on several benchmark ranking datasets, our experimental results show that this direction is applicable.

今年我们的主要任务是开发基于大规模数据集的联邦信息检索模型。为此，我们首先将信息检索视为用户与搜索引擎系统之间的交互过程，而不是每个查询的独立排名。其次，我们探讨如何有效整合在线排序学习和联邦学习。具体来说，在线学习排名使我们能够应对上述交互过程。联邦学习使我们能够通过在设备上学习排名模型来处理隐私问题。基于对多个基准排名数据集的一系列实验，我们的实验结果表明该方向是适用的。

项目成果

単語の感情属性を活かしたロボット教師の表情生成

利用单词的情感属性生成机器人教师的面部表情

• 发表时间: 2020
• 作者: 房登 淳平;康 シン;西出 俊;任 福継
• 通讯作者: 任 福継

TUA1 at the TREC 2019: Deep Learning Track

• 发表时间: 2019
• 作者: Yun Gao;Xin Kang;F. Ren;Haitao Yu

Dalian University of Technology(中国)

大连理工大学（中国）

FLAME: Differentially Private Federated Learning in the Shuffle Model

• DOI: 10.1609/aaai.v35i10.17053
• 发表时间: 2020-09
• 作者: Ruixuan Liu;Yang Cao;Hong Chen;Ruoyang Guo;Masatoshi Yoshikawa

PPIR

PPIR