World Wide Web-Internet and Web Information Systems最新文献_第10页

Next location recommendation: a multi-context features integration perspective 下一个位置推荐:多上下文功能集成视角

IF 3.7 3区计算机科学

World Wide Web-Internet and Web Information Systems Pub Date : 2022-12-16 DOI: 10.1007/s11280-022-01126-y

Xuemei Wei, Chunli Liu, Yezheng Liu, Yang Li, Kai Zhang

引用次数: 0

PerHeFed: A general framework of personalized federated learning for heterogeneous convolutional neural networks. PerHeFed：异构卷积神经网络个性化联合学习通用框架

IF 3.7 3区计算机科学

World Wide Web-Internet and Web Information Systems Pub Date : 2022-12-12 DOI: 10.1007/s11280-022-01119-x

Le Ma, YuYing Liao, Bin Zhou, Wen Xi

{"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":"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.","PeriodicalId":49356,"journal":{"name":"World Wide Web-Internet and Web Information Systems","volume":null,"pages":null},"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}

引用次数: 0

Auto-regressive extractive summarization with replacement 带有替换的自动回归提取摘要

IF 3.7 3区计算机科学

World Wide Web-Internet and Web Information Systems Pub Date : 2022-12-09 DOI: 10.1007/s11280-022-01108-0

Tianyu Zhu, Wen Hua, Jianfeng Qu, S. Hosseini, Xiaofang Zhou

引用次数: 2

Hierarchical filtering: improving similar substring matching under edit distance 分层过滤:改进编辑距离下的相似子字符串匹配

IF 3.7 3区计算机科学

World Wide Web-Internet and Web Information Systems Pub Date : 2022-12-06 DOI: 10.1007/s11280-022-01128-w

Tao Qiu, Chuanyu Zong, Xiaochun Yang, Bin Wang, Bingxian Li

引用次数: 0

TULRN: Trajectory user linking on road networks turrn:道路网络上的轨迹用户链接

IF 3.7 3区计算机科学

World Wide Web-Internet and Web Information Systems Pub Date : 2022-12-01 DOI: 10.1007/s11280-022-01124-0

Yu Sang, Zhenping Xie, Wei Chen, Lei Zhao

引用次数: 1

Continuous spatial keyword search with query result diversifications 具有多样化查询结果的连续空间关键字搜索

IF 3.7 3区计算机科学

World Wide Web-Internet and Web Information Systems Pub Date : 2022-11-25 DOI: 10.1007/s11280-022-01118-y

Ying Zhong, Jianmin Li, Shunzhi Zhu

引用次数: 1

HGNN-ETA: Heterogeneous graph neural network enriched with text attribute HGNN-ETA:富含文本属性的异构图神经网络

IF 3.7 3区计算机科学

World Wide Web-Internet and Web Information Systems Pub Date : 2022-11-23 DOI: 10.1007/s11280-022-01120-4

C. Li, Zhen Wang, Zhongying Zhao, H. Duan, Q. Zeng

引用次数: 0

Intellectual property protection of DNN models DNN模型的知识产权保护

IF 3.7 3区计算机科学

World Wide Web-Internet and Web Information Systems Pub Date : 2022-11-22 DOI: 10.1007/s11280-022-01113-3

Sen Peng, Yufei Chen, Jie Xu, Zizhuo Chen, Cong Wang, Xiaohua Jia

引用次数: 3

Top-k heavy weight triangles listing on graph stream 在图流上列出Top-k个重权重三角形

IF 3.7 3区计算机科学

World Wide Web-Internet and Web Information Systems Pub Date : 2022-11-17 DOI: 10.1007/s11280-022-01117-z

Fan Zhang, Xiangyang Gou, Lei Zou

引用次数: 1

A text and GNN based controversy detection method on social media 基于文本和GNN的社交媒体争议检测方法

IF 3.7 3区计算机科学

World Wide Web-Internet and Web Information Systems Pub Date : 2022-11-17 DOI: 10.1007/s11280-022-01116-0

Samy Benslimane, J. Azé, S. Bringay, Maximilien Servajean, C. Mollevi

引用次数: 3