FedTour: Participatory Federated Learning of Tourism Object Recognition Models with Minimal Parameter Exchanges between User Devices

Shusaku Tomita, Jose Paolo Talusan, Yugo Nakamura, Hirohiko Suwa, Keiichi Yasumoto

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

抄録

In this paper, we propose FedTour, a federated learning-based method for training tourism object recognition models, which utilizes short-distance direct communication between user devices and maximizes the model performance within a limited number of updates. In FedTour, whenever two user devices are within range, they first exchange metadata including the learning degree (e.g., recognition accuracy) of their models, and determine whether it is effective to integrate the peer model by using a regressor trained with various pairs of models with different accuracy to predict the accuracy of the merged model. Once it is deemed effective, the model parameters are exchanged and the model is updated using FedAvg (averaging weights of two models of user devices). By carefully setting the threshold of whether FedAvg is applied or not, model performance is improved within a limited number of model parameter exchanges resulting in lower power consumption of user devices. We conducted a simulation using mobile phone trace data of actual users in a real sightseeing area and evaluated the improvement in accuracy of a CNN model that recognizes 10 objects while limiting the number of model parameter exchanges to only 40. Results show FedTour increased the initial model accuracy by 112%, while the baseline gossip-based method achieved 69%.

本文言語英語
ホスト出版物のタイトル2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2022
出版社Institute of Electrical and Electronics Engineers Inc.
ページ667-673
ページ数7
ISBN(電子版)9781665416474
DOI
出版ステータス出版済み - 2022
イベント2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2022 - Pisa, イタリア
継続期間: 3月 21 20223月 25 2022

出版物シリーズ

名前2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2022

会議

会議2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, PerCom Workshops 2022
国/地域イタリア
CityPisa
Period3/21/223/25/22

!!!All Science Journal Classification (ASJC) codes

  • 人工知能
  • モデリングとシミュレーション
  • 健康情報学
  • コンピュータ ネットワークおよび通信
  • コンピュータ サイエンスの応用
  • 情報システム
  • 情報システムおよび情報管理
  • 安全性、リスク、信頼性、品質管理

フィンガープリント

「FedTour: Participatory Federated Learning of Tourism Object Recognition Models with Minimal Parameter Exchanges between User Devices」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル