Labeled data is widely used in various classification tasks.However,there is a huge challenge that labels are often added artificially.Wrong labels added by malicious users will affect the training effect of the model...Labeled data is widely used in various classification tasks.However,there is a huge challenge that labels are often added artificially.Wrong labels added by malicious users will affect the training effect of the model.The unreliability of labeled data has hindered the research.In order to solve the above problems,we propose a framework of Label Noise Filtering and Missing Label Supplement(LNFS).And we take location labels in Location-Based Social Networks(LBSN)as an example to implement our framework.For the problem of label noise filtering,we first use FastText to transform the restaurant's labels into vectors,and then based on the assumption that the label most similar to all other labels in the location is most representative.We use cosine similarity to judge and select the most representative label.For the problem of label missing,we use simple common word similarity to judge the similarity of users'comments,and then use the label of the similar restaurant to supplement the missing labels.To optimize the performance of the model,we introduce game theory into our model to simulate the game between the malicious users and the model to improve the reliability of the model.Finally,a case study is given to illustrate the effectiveness and reliability of LNFS.展开更多
Cross-Domain Recommendation(CDR)aims to solve data sparsity and cold-start problems by utilizing a relatively information-rich source domain to improve the recommendation performance of the data-sparse target domain.H...Cross-Domain Recommendation(CDR)aims to solve data sparsity and cold-start problems by utilizing a relatively information-rich source domain to improve the recommendation performance of the data-sparse target domain.However,most existing approaches rely on the assumption of centralized storage of user data,which undoubtedly poses a significant risk of user privacy leakage because user data are highly privacy-sensitive.To this end,we propose a privacy-preserving Federated framework for Cross-Domain Recommendation,called FedCDR.In our method,to avoid leakage of user privacy,a general recommendation model is trained on each user's personal device to obtain embeddings of users and items,and each client uploads weights to the central server.The central server then aggregates the weights and distributes them to each client for updating.Furthermore,because the weights implicitly contain private information about the user,local differential privacy is adopted for the gradients before uploading them to the server for better protection of user privacy.To distill the relationship of user embedding between two domains,an embedding transformation mechanism is used on the server side to learn the cross-domain embedding transformation model.Extensive experiments on real-world datasets demonstrate that ourmethod achieves performance comparable with that of existing data-centralized methods and effectively protects user privacy.展开更多
In the mobile edge computing environments,Quality of Service(QoS)prediction plays a crucial role in web service recommendation.Because of distinct features of mobile edge computing,i.e.,the mobility of users and incom...In the mobile edge computing environments,Quality of Service(QoS)prediction plays a crucial role in web service recommendation.Because of distinct features of mobile edge computing,i.e.,the mobility of users and incomplete historical QoS data,traditional QoS prediction approaches may obtain less accurate results in the mobile edge computing environments.In this paper,we treat the historical QoS values at different time slots as a temporal sequence of QoS matrices.By incorporating the compressed matrices extracted from QoS matrices through truncated Singular Value Decomposition(SVD)with the classical ARIMA model,we extend the ARIMA model to predict multiple QoS values simultaneously and efficiently.Experimental results show that our proposed approach outperforms the other state-of-the-art approaches in accuracy and efficiency.展开更多
基金supported by the National Natural Science Foundation of China(No.61872219)the Natural Science Foundation of Shandong Province(ZR2019MF001).
文摘Labeled data is widely used in various classification tasks.However,there is a huge challenge that labels are often added artificially.Wrong labels added by malicious users will affect the training effect of the model.The unreliability of labeled data has hindered the research.In order to solve the above problems,we propose a framework of Label Noise Filtering and Missing Label Supplement(LNFS).And we take location labels in Location-Based Social Networks(LBSN)as an example to implement our framework.For the problem of label noise filtering,we first use FastText to transform the restaurant's labels into vectors,and then based on the assumption that the label most similar to all other labels in the location is most representative.We use cosine similarity to judge and select the most representative label.For the problem of label missing,we use simple common word similarity to judge the similarity of users'comments,and then use the label of the similar restaurant to supplement the missing labels.To optimize the performance of the model,we introduce game theory into our model to simulate the game between the malicious users and the model to improve the reliability of the model.Finally,a case study is given to illustrate the effectiveness and reliability of LNFS.
基金supported by the Key Project of Nature Science Research for the Universities of Anhui Province of China(No.KJ2020A0657)the National Science Foundation of China(No.61872002)the Key Research and Development Program of Anhui Province(No.202104a05020058).
文摘Cross-Domain Recommendation(CDR)aims to solve data sparsity and cold-start problems by utilizing a relatively information-rich source domain to improve the recommendation performance of the data-sparse target domain.However,most existing approaches rely on the assumption of centralized storage of user data,which undoubtedly poses a significant risk of user privacy leakage because user data are highly privacy-sensitive.To this end,we propose a privacy-preserving Federated framework for Cross-Domain Recommendation,called FedCDR.In our method,to avoid leakage of user privacy,a general recommendation model is trained on each user's personal device to obtain embeddings of users and items,and each client uploads weights to the central server.The central server then aggregates the weights and distributes them to each client for updating.Furthermore,because the weights implicitly contain private information about the user,local differential privacy is adopted for the gradients before uploading them to the server for better protection of user privacy.To distill the relationship of user embedding between two domains,an embedding transformation mechanism is used on the server side to learn the cross-domain embedding transformation model.Extensive experiments on real-world datasets demonstrate that ourmethod achieves performance comparable with that of existing data-centralized methods and effectively protects user privacy.
文摘In the mobile edge computing environments,Quality of Service(QoS)prediction plays a crucial role in web service recommendation.Because of distinct features of mobile edge computing,i.e.,the mobility of users and incomplete historical QoS data,traditional QoS prediction approaches may obtain less accurate results in the mobile edge computing environments.In this paper,we treat the historical QoS values at different time slots as a temporal sequence of QoS matrices.By incorporating the compressed matrices extracted from QoS matrices through truncated Singular Value Decomposition(SVD)with the classical ARIMA model,we extend the ARIMA model to predict multiple QoS values simultaneously and efficiently.Experimental results show that our proposed approach outperforms the other state-of-the-art approaches in accuracy and efficiency.
