Chaoqun Yang, Wei Yuan, Liang Qu, Thanh Tam Nguyen
{"title":"PDC-FRS:联盟推荐系统的隐私保护数据贡献","authors":"Chaoqun Yang, Wei Yuan, Liang Qu, Thanh Tam Nguyen","doi":"arxiv-2409.07773","DOIUrl":null,"url":null,"abstract":"Federated recommender systems (FedRecs) have emerged as a popular research\ndirection for protecting users' privacy in on-device recommendations. In\nFedRecs, users keep their data locally and only contribute their local\ncollaborative information by uploading model parameters to a central server.\nWhile this rigid framework protects users' raw data during training, it\nseverely compromises the recommendation model's performance due to the\nfollowing reasons: (1) Due to the power law distribution nature of user\nbehavior data, individual users have few data points to train a recommendation\nmodel, resulting in uploaded model updates that may be far from optimal; (2) As\neach user's uploaded parameters are learned from local data, which lacks global\ncollaborative information, relying solely on parameter aggregation methods such\nas FedAvg to fuse global collaborative information may be suboptimal. To bridge\nthis performance gap, we propose a novel federated recommendation framework,\nPDC-FRS. Specifically, we design a privacy-preserving data contribution\nmechanism that allows users to share their data with a differential privacy\nguarantee. Based on the shared but perturbed data, an auxiliary model is\ntrained in parallel with the original federated recommendation process. This\nauxiliary model enhances FedRec by augmenting each user's local dataset and\nintegrating global collaborative information. To demonstrate the effectiveness\nof PDC-FRS, we conduct extensive experiments on two widely used recommendation\ndatasets. The empirical results showcase the superiority of PDC-FRS compared to\nbaseline methods.","PeriodicalId":501281,"journal":{"name":"arXiv - CS - Information Retrieval","volume":"404 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"PDC-FRS: Privacy-preserving Data Contribution for Federated Recommender System\",\"authors\":\"Chaoqun Yang, Wei Yuan, Liang Qu, Thanh Tam Nguyen\",\"doi\":\"arxiv-2409.07773\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Federated recommender systems (FedRecs) have emerged as a popular research\\ndirection for protecting users' privacy in on-device recommendations. In\\nFedRecs, users keep their data locally and only contribute their local\\ncollaborative information by uploading model parameters to a central server.\\nWhile this rigid framework protects users' raw data during training, it\\nseverely compromises the recommendation model's performance due to the\\nfollowing reasons: (1) Due to the power law distribution nature of user\\nbehavior data, individual users have few data points to train a recommendation\\nmodel, resulting in uploaded model updates that may be far from optimal; (2) As\\neach user's uploaded parameters are learned from local data, which lacks global\\ncollaborative information, relying solely on parameter aggregation methods such\\nas FedAvg to fuse global collaborative information may be suboptimal. To bridge\\nthis performance gap, we propose a novel federated recommendation framework,\\nPDC-FRS. Specifically, we design a privacy-preserving data contribution\\nmechanism that allows users to share their data with a differential privacy\\nguarantee. Based on the shared but perturbed data, an auxiliary model is\\ntrained in parallel with the original federated recommendation process. This\\nauxiliary model enhances FedRec by augmenting each user's local dataset and\\nintegrating global collaborative information. To demonstrate the effectiveness\\nof PDC-FRS, we conduct extensive experiments on two widely used recommendation\\ndatasets. The empirical results showcase the superiority of PDC-FRS compared to\\nbaseline methods.\",\"PeriodicalId\":501281,\"journal\":{\"name\":\"arXiv - CS - Information Retrieval\",\"volume\":\"404 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Information Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07773\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Information Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07773","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
PDC-FRS: Privacy-preserving Data Contribution for Federated Recommender System
Federated recommender systems (FedRecs) have emerged as a popular research
direction for protecting users' privacy in on-device recommendations. In
FedRecs, users keep their data locally and only contribute their local
collaborative information by uploading model parameters to a central server.
While this rigid framework protects users' raw data during training, it
severely compromises the recommendation model's performance due to the
following reasons: (1) Due to the power law distribution nature of user
behavior data, individual users have few data points to train a recommendation
model, resulting in uploaded model updates that may be far from optimal; (2) As
each user's uploaded parameters are learned from local data, which lacks global
collaborative information, relying solely on parameter aggregation methods such
as FedAvg to fuse global collaborative information may be suboptimal. To bridge
this performance gap, we propose a novel federated recommendation framework,
PDC-FRS. Specifically, we design a privacy-preserving data contribution
mechanism that allows users to share their data with a differential privacy
guarantee. Based on the shared but perturbed data, an auxiliary model is
trained in parallel with the original federated recommendation process. This
auxiliary model enhances FedRec by augmenting each user's local dataset and
integrating global collaborative information. To demonstrate the effectiveness
of PDC-FRS, we conduct extensive experiments on two widely used recommendation
datasets. The empirical results showcase the superiority of PDC-FRS compared to
baseline methods.