{"title":"HPFL:基于异构隐私敏感水平融合多传感器模式的联邦学习","authors":"Yuanjie Chen, Chih-Fan Hsu, Chung-Chi Tsai, Cheng-Hsin Hsu","doi":"10.1145/3552487.3556438","DOIUrl":null,"url":null,"abstract":"Solving classification problems to understand multi-modality sensor data has become popular, but rich-media sensors, e.g., RGB cameras and microphones, are privacy-invasive. Though existing Federated Learning (FL) algorithms allow clients to keep their sensor data private, they suffer from degraded performance, particularly lower classification accuracy and longer training time, than centralized learning. We propose a Heterogeneous Privacy Federated Learning (HPFL) paradigm to capitalize on the information in the privacy insensitive data (such as mmWave point clouds) while keeping the privacy sensitive data (such as RGB images) private because sensor data are of diverse sensitivity levels. We evaluate the HPFL paradigm on two representative classification problems: semantic segmentation and emotion recognition. Extensive experiments demonstrate that the HPFL paradigm outperforms: (i) the popular FedAvg by 18.20% in foreground accuracy (semantic segmentation) and 4.20% in F1-score (emotion recognition) under non-i.i.d. sample distributions and (ii) the state-of-the-art FL algorithms by 12.40%--17.70% in foreground accuracy and 2.54%--4.10% in F1-score.","PeriodicalId":274055,"journal":{"name":"Proceedings of the 1st International Workshop on Methodologies for Multimedia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"HPFL: Federated Learning by Fusing Multiple Sensor Modalities with Heterogeneous Privacy Sensitivity Levels\",\"authors\":\"Yuanjie Chen, Chih-Fan Hsu, Chung-Chi Tsai, Cheng-Hsin Hsu\",\"doi\":\"10.1145/3552487.3556438\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Solving classification problems to understand multi-modality sensor data has become popular, but rich-media sensors, e.g., RGB cameras and microphones, are privacy-invasive. Though existing Federated Learning (FL) algorithms allow clients to keep their sensor data private, they suffer from degraded performance, particularly lower classification accuracy and longer training time, than centralized learning. We propose a Heterogeneous Privacy Federated Learning (HPFL) paradigm to capitalize on the information in the privacy insensitive data (such as mmWave point clouds) while keeping the privacy sensitive data (such as RGB images) private because sensor data are of diverse sensitivity levels. We evaluate the HPFL paradigm on two representative classification problems: semantic segmentation and emotion recognition. Extensive experiments demonstrate that the HPFL paradigm outperforms: (i) the popular FedAvg by 18.20% in foreground accuracy (semantic segmentation) and 4.20% in F1-score (emotion recognition) under non-i.i.d. sample distributions and (ii) the state-of-the-art FL algorithms by 12.40%--17.70% in foreground accuracy and 2.54%--4.10% in F1-score.\",\"PeriodicalId\":274055,\"journal\":{\"name\":\"Proceedings of the 1st International Workshop on Methodologies for Multimedia\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-10-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 1st International Workshop on Methodologies for Multimedia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3552487.3556438\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 1st International Workshop on Methodologies for Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3552487.3556438","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
HPFL: Federated Learning by Fusing Multiple Sensor Modalities with Heterogeneous Privacy Sensitivity Levels
Solving classification problems to understand multi-modality sensor data has become popular, but rich-media sensors, e.g., RGB cameras and microphones, are privacy-invasive. Though existing Federated Learning (FL) algorithms allow clients to keep their sensor data private, they suffer from degraded performance, particularly lower classification accuracy and longer training time, than centralized learning. We propose a Heterogeneous Privacy Federated Learning (HPFL) paradigm to capitalize on the information in the privacy insensitive data (such as mmWave point clouds) while keeping the privacy sensitive data (such as RGB images) private because sensor data are of diverse sensitivity levels. We evaluate the HPFL paradigm on two representative classification problems: semantic segmentation and emotion recognition. Extensive experiments demonstrate that the HPFL paradigm outperforms: (i) the popular FedAvg by 18.20% in foreground accuracy (semantic segmentation) and 4.20% in F1-score (emotion recognition) under non-i.i.d. sample distributions and (ii) the state-of-the-art FL algorithms by 12.40%--17.70% in foreground accuracy and 2.54%--4.10% in F1-score.