Pub Date : 2022-12-16DOI: 10.1007/s11280-022-01126-y
Xuemei Wei, Chunli Liu, Yezheng Liu, Yang Li, Kai Zhang
{"title":"Next location recommendation: a multi-context features integration perspective","authors":"Xuemei Wei, Chunli Liu, Yezheng Liu, Yang Li, Kai Zhang","doi":"10.1007/s11280-022-01126-y","DOIUrl":"https://doi.org/10.1007/s11280-022-01126-y","url":null,"abstract":"","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":"1 1","pages":"2051-2074"},"PeriodicalIF":3.7,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76937248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-12DOI: 10.1007/s11280-022-01119-x
Le Ma, YuYing Liao, Bin Zhou, Wen Xi
In conventional federated learning, each device is restricted to train a network model of the same structure. This greatly hinders the application of federated learning where the data and devices are quite heterogeneous because of their different hardware equipment and communication networks. At the same time, existing studies have shown that transmitting all of the model parameters not only has heavy communication costs, but also increases risk of privacy leakage. We propose a general framework for personalized federated learning (PerHeFed), which enables the devices to design their local model structures autonomously and share sub-models without structural restrictions. In PerHeFed, a simple-but-effective mapping relation and a novel personalized sub-model aggregation method are proposed for heterogeneous sub-models to be aggregated. By dividing the aggregations into two primitive types (i.e., inter-layer and intra-layer), PerHeFed is applicable to any combination of heterogeneous convolutional neural networks, and we believe that this can satisfy the personalized requirements of heterogeneous models. Experiments show that, compared to the state-of-the-art method (e.g., FLOP), in non-IID data sets our method compress ≈ 50% of the shared sub-model parameters with only a 4.38% drop in accuracy on SVHN dataset and on CIFAR-10, PerHeFed even achieves a 0.3% improvement in accuracy. To the best of our knowledge, our work is the first general personalized federated learning framework for heterogeneous convolutional networks, even cross different networks, addressing model structure unity in conventional federated learning.
{"title":"PerHeFed: A general framework of personalized federated learning for heterogeneous convolutional neural networks.","authors":"Le Ma, YuYing Liao, Bin Zhou, Wen Xi","doi":"10.1007/s11280-022-01119-x","DOIUrl":"10.1007/s11280-022-01119-x","url":null,"abstract":"<p><p>In conventional federated learning, each device is restricted to train a network model of the same structure. This greatly hinders the application of federated learning where the data and devices are quite heterogeneous because of their different hardware equipment and communication networks. At the same time, existing studies have shown that transmitting all of the model parameters not only has heavy communication costs, but also increases risk of privacy leakage. We propose a general framework for personalized federated learning (PerHeFed), which enables the devices to design their local model structures autonomously and share sub-models without structural restrictions. In PerHeFed, a simple-but-effective mapping relation and a novel personalized sub-model aggregation method are proposed for heterogeneous sub-models to be aggregated. By dividing the aggregations into two primitive types (i.e., inter-layer and intra-layer), PerHeFed is applicable to any combination of heterogeneous convolutional neural networks, and we believe that this can satisfy the personalized requirements of heterogeneous models. Experiments show that, compared to the state-of-the-art method (e.g., FLOP), in non-IID data sets our method compress ≈ 50<i>%</i> of the shared sub-model parameters with only a 4.38% drop in accuracy on SVHN dataset and on CIFAR-10, PerHeFed even achieves a 0.3% improvement in accuracy. To the best of our knowledge, our work is the first general personalized federated learning framework for heterogeneous convolutional networks, even cross different networks, addressing model structure unity in conventional federated learning.</p>","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":" ","pages":"1-23"},"PeriodicalIF":3.7,"publicationDate":"2022-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9743105/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10404913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-09DOI: 10.1007/s11280-022-01108-0
Tianyu Zhu, Wen Hua, Jianfeng Qu, S. Hosseini, Xiaofang Zhou
{"title":"Auto-regressive extractive summarization with replacement","authors":"Tianyu Zhu, Wen Hua, Jianfeng Qu, S. Hosseini, Xiaofang Zhou","doi":"10.1007/s11280-022-01108-0","DOIUrl":"https://doi.org/10.1007/s11280-022-01108-0","url":null,"abstract":"","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":"29 1","pages":"2003-2026"},"PeriodicalIF":3.7,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81726126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-06DOI: 10.1007/s11280-022-01128-w
Tao Qiu, Chuanyu Zong, Xiaochun Yang, Bin Wang, Bingxian Li
{"title":"Hierarchical filtering: improving similar substring matching under edit distance","authors":"Tao Qiu, Chuanyu Zong, Xiaochun Yang, Bin Wang, Bingxian Li","doi":"10.1007/s11280-022-01128-w","DOIUrl":"https://doi.org/10.1007/s11280-022-01128-w","url":null,"abstract":"","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":"78 1","pages":"1967-2001"},"PeriodicalIF":3.7,"publicationDate":"2022-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83318874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-01DOI: 10.1007/s11280-022-01124-0
Yu Sang, Zhenping Xie, Wei Chen, Lei Zhao
{"title":"TULRN: Trajectory user linking on road networks","authors":"Yu Sang, Zhenping Xie, Wei Chen, Lei Zhao","doi":"10.1007/s11280-022-01124-0","DOIUrl":"https://doi.org/10.1007/s11280-022-01124-0","url":null,"abstract":"","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":"22 1","pages":"1949-1965"},"PeriodicalIF":3.7,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89079342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-25DOI: 10.1007/s11280-022-01118-y
Ying Zhong, Jianmin Li, Shunzhi Zhu
{"title":"Continuous spatial keyword search with query result diversifications","authors":"Ying Zhong, Jianmin Li, Shunzhi Zhu","doi":"10.1007/s11280-022-01118-y","DOIUrl":"https://doi.org/10.1007/s11280-022-01118-y","url":null,"abstract":"","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":"6 1","pages":"1935-1948"},"PeriodicalIF":3.7,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83622325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-23DOI: 10.1007/s11280-022-01120-4
C. Li, Zhen Wang, Zhongying Zhao, H. Duan, Q. Zeng
{"title":"HGNN-ETA: Heterogeneous graph neural network enriched with text attribute","authors":"C. Li, Zhen Wang, Zhongying Zhao, H. Duan, Q. Zeng","doi":"10.1007/s11280-022-01120-4","DOIUrl":"https://doi.org/10.1007/s11280-022-01120-4","url":null,"abstract":"","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":"72 1","pages":"1913-1934"},"PeriodicalIF":3.7,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88150637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-22DOI: 10.1007/s11280-022-01113-3
Sen Peng, Yufei Chen, Jie Xu, Zizhuo Chen, Cong Wang, Xiaohua Jia
{"title":"Intellectual property protection of DNN models","authors":"Sen Peng, Yufei Chen, Jie Xu, Zizhuo Chen, Cong Wang, Xiaohua Jia","doi":"10.1007/s11280-022-01113-3","DOIUrl":"https://doi.org/10.1007/s11280-022-01113-3","url":null,"abstract":"","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":"553 1","pages":"1877-1911"},"PeriodicalIF":3.7,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77147748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-17DOI: 10.1007/s11280-022-01116-0
Samy Benslimane, J. Azé, S. Bringay, Maximilien Servajean, C. Mollevi
{"title":"A text and GNN based controversy detection method on social media","authors":"Samy Benslimane, J. Azé, S. Bringay, Maximilien Servajean, C. Mollevi","doi":"10.1007/s11280-022-01116-0","DOIUrl":"https://doi.org/10.1007/s11280-022-01116-0","url":null,"abstract":"","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":"19 1","pages":"799-825"},"PeriodicalIF":3.7,"publicationDate":"2022-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78959522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-17DOI: 10.1007/s11280-022-01117-z
Fan Zhang, Xiangyang Gou, Lei Zou
{"title":"Top-k heavy weight triangles listing on graph stream","authors":"Fan Zhang, Xiangyang Gou, Lei Zou","doi":"10.1007/s11280-022-01117-z","DOIUrl":"https://doi.org/10.1007/s11280-022-01117-z","url":null,"abstract":"","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":"12 1","pages":"1827-1851"},"PeriodicalIF":3.7,"publicationDate":"2022-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86595735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号