The forthcoming sixth generation(6G)of mobile communication networks is envisioned to be AInative,supporting intelligent services and pervasive computing at unprecedented scale.Among the key paradigms enabling this vi...The forthcoming sixth generation(6G)of mobile communication networks is envisioned to be AInative,supporting intelligent services and pervasive computing at unprecedented scale.Among the key paradigms enabling this vision,Federated Learning(FL)has gained prominence as a distributed machine learning framework that allows multiple devices to collaboratively train models without sharing raw data,thereby preserving privacy and reducing the need for centralized storage.This capability is particularly attractive for vision-based applications,where image and video data are both sensitive and bandwidth-intensive.However,the integration of FL with 6G networks presents unique challenges,including communication bottlenecks,device heterogeneity,and trade-offs between model accuracy,latency,and energy consumption.In this paper,we developed a simulation-based framework to investigate the performance of FL in representative vision tasks under 6G-like environments.We formalize the system model,incorporating both the federated averaging(FedAvg)training process and a simplified communication costmodel that captures bandwidth constraints,packet loss,and variable latency across edge devices.Using standard image datasets(e.g.,MNIST,CIFAR-10)as benchmarks,we analyze how factors such as the number of participating clients,degree of data heterogeneity,and communication frequency influence convergence speed and model accuracy.Additionally,we evaluate the effectiveness of lightweight communication-efficient strategies,including local update tuning and gradient compression,in mitigating network overhead.The experimental results reveal several key insights:(i)communication limitations can significantly degrade FL convergence in vision tasks if not properly addressed;(ii)judicious tuning of local training epochs and client participation levels enables notable improvements in both efficiency and accuracy;and(iii)communication-efficient FL strategies provide a promising pathway to balance performance with the stringent latency and reliability requirements expected in 6G.These findings highlight the synergistic role of AI and nextgeneration networks in enabling privacy-preserving,real-time vision applications,and they provide concrete design guidelines for researchers and practitioners working at the intersection of FL and 6G.展开更多
In this study,we address a demanding time series forecasting problem that deals simultaneously with the following:(1)intermittent time series,(2)multi-step ahead forecasting,(3)time series with multiple seasonal perio...In this study,we address a demanding time series forecasting problem that deals simultaneously with the following:(1)intermittent time series,(2)multi-step ahead forecasting,(3)time series with multiple seasonal periods,and(4)performance measures for model selection across multiple time series.Current literature deals with these types of problems separately,and no study has dealt with all these characteristics simultaneously.To fill this knowledge gap,we begin by reviewing all the necessary existing literature relevant to this case study with the goal of proposing a framework capable of achieving adequate forecast accuracy for such a complex problem.Several adaptions and innovations have been conducted,which are marked as contributions to the literature.Specifically,we proposed a weighted average forecast combination of many cutting-edge models based on their out-of-sample performance.To gather strong evidence that our ensemble model works in practice,we undertook a large-scale study across 98 time series,rigorously assessed with unbiased performance measures,where a week seasonal naïve was set as a benchmark.The results demonstrate that the proposed ensemble model achieves eyecatching forecasting accuracy.展开更多
Since 2014,"Bring Your Own Data"workshops(BYODs)have been organised to inform people about the process and benefits of making resources Findable,Accessible,Interoperable,and Reusable(FAIR,and the FAIRificati...Since 2014,"Bring Your Own Data"workshops(BYODs)have been organised to inform people about the process and benefits of making resources Findable,Accessible,Interoperable,and Reusable(FAIR,and the FAIRification process).The BYOD workshops'content and format differ depending on their goal,context,and the background and needs of participants.Data-focused BYODs educate domain experts on how to make their data FAIR to find new answers to research questions.Management-focused BYODs promote the benefits of making data FAIR and instruct project managers and policy-makers on the characteristics of FAIRification projects.Software-focused BYODs gather software developers and experts on FAIR to implement or improve software resources that are used to support FAIRification.Overall,these BYODs intend to foster collaboration between different types of stakeholders involved in data management,curation,and reuse(e.g.domain experts,trainers,developers,data owners,data analysts,FAIR experts).The BYODs also serve as an opportunity to learn what kind of support for FAIRification is needed from different communities and to develop teaching materials based on practical examples and experience.In this paper,we detail the three different structures of the BYODs and describe examples of early BYODs related to plant breeding data,and rare disease registries and biobanks,which have shaped the structure of the workshops.We discuss the latest insights into making BYODs more productive by leveraging our almost ten years of training experience in these workshops,including successes and encountered challenges.Finally,we examine how the participants'feedback has motivated the research on FAIR,including the development of workflows and software.展开更多
文摘The forthcoming sixth generation(6G)of mobile communication networks is envisioned to be AInative,supporting intelligent services and pervasive computing at unprecedented scale.Among the key paradigms enabling this vision,Federated Learning(FL)has gained prominence as a distributed machine learning framework that allows multiple devices to collaboratively train models without sharing raw data,thereby preserving privacy and reducing the need for centralized storage.This capability is particularly attractive for vision-based applications,where image and video data are both sensitive and bandwidth-intensive.However,the integration of FL with 6G networks presents unique challenges,including communication bottlenecks,device heterogeneity,and trade-offs between model accuracy,latency,and energy consumption.In this paper,we developed a simulation-based framework to investigate the performance of FL in representative vision tasks under 6G-like environments.We formalize the system model,incorporating both the federated averaging(FedAvg)training process and a simplified communication costmodel that captures bandwidth constraints,packet loss,and variable latency across edge devices.Using standard image datasets(e.g.,MNIST,CIFAR-10)as benchmarks,we analyze how factors such as the number of participating clients,degree of data heterogeneity,and communication frequency influence convergence speed and model accuracy.Additionally,we evaluate the effectiveness of lightweight communication-efficient strategies,including local update tuning and gradient compression,in mitigating network overhead.The experimental results reveal several key insights:(i)communication limitations can significantly degrade FL convergence in vision tasks if not properly addressed;(ii)judicious tuning of local training epochs and client participation levels enables notable improvements in both efficiency and accuracy;and(iii)communication-efficient FL strategies provide a promising pathway to balance performance with the stringent latency and reliability requirements expected in 6G.These findings highlight the synergistic role of AI and nextgeneration networks in enabling privacy-preserving,real-time vision applications,and they provide concrete design guidelines for researchers and practitioners working at the intersection of FL and 6G.
基金supported by COMPETE:POCI-01-0247-FEDER-039719 and FCT-Fundação para a Ciência e Tecnologia within the Project Scope:UIDB/00127/2020.
文摘In this study,we address a demanding time series forecasting problem that deals simultaneously with the following:(1)intermittent time series,(2)multi-step ahead forecasting,(3)time series with multiple seasonal periods,and(4)performance measures for model selection across multiple time series.Current literature deals with these types of problems separately,and no study has dealt with all these characteristics simultaneously.To fill this knowledge gap,we begin by reviewing all the necessary existing literature relevant to this case study with the goal of proposing a framework capable of achieving adequate forecast accuracy for such a complex problem.Several adaptions and innovations have been conducted,which are marked as contributions to the literature.Specifically,we proposed a weighted average forecast combination of many cutting-edge models based on their out-of-sample performance.To gather strong evidence that our ensemble model works in practice,we undertook a large-scale study across 98 time series,rigorously assessed with unbiased performance measures,where a week seasonal naïve was set as a benchmark.The results demonstrate that the proposed ensemble model achieves eyecatching forecasting accuracy.
基金support from the RD-Connect project(funded from the European Community's Seventh Framework Program under grant agreement n°305444"RD-CONNECT")ELIXIR and ELIXIR-EXCELERATE(Grant number EU H2020#676559)+1 种基金the Istituto Superiore di Sanita(ISS),the Leiden University Medical Center(LUMC)the University Medical Center Groningen,and the Dutch Techcentre for Life Sciences(DTL)between 2014 and 2018.From 2019 to 2023,the RD-BYOD has been funded by the European Joint Programme Rare Diseases(EJP RD)and its partners(European Union Horizon 2020 Research and Innovation Programme under Grant Agreement n°825575),and we are grateful for their continued support.
文摘Since 2014,"Bring Your Own Data"workshops(BYODs)have been organised to inform people about the process and benefits of making resources Findable,Accessible,Interoperable,and Reusable(FAIR,and the FAIRification process).The BYOD workshops'content and format differ depending on their goal,context,and the background and needs of participants.Data-focused BYODs educate domain experts on how to make their data FAIR to find new answers to research questions.Management-focused BYODs promote the benefits of making data FAIR and instruct project managers and policy-makers on the characteristics of FAIRification projects.Software-focused BYODs gather software developers and experts on FAIR to implement or improve software resources that are used to support FAIRification.Overall,these BYODs intend to foster collaboration between different types of stakeholders involved in data management,curation,and reuse(e.g.domain experts,trainers,developers,data owners,data analysts,FAIR experts).The BYODs also serve as an opportunity to learn what kind of support for FAIRification is needed from different communities and to develop teaching materials based on practical examples and experience.In this paper,we detail the three different structures of the BYODs and describe examples of early BYODs related to plant breeding data,and rare disease registries and biobanks,which have shaped the structure of the workshops.We discuss the latest insights into making BYODs more productive by leveraging our almost ten years of training experience in these workshops,including successes and encountered challenges.Finally,we examine how the participants'feedback has motivated the research on FAIR,including the development of workflows and software.
