Pub Date : 2022-07-01DOI: 10.1109/ICDCS54860.2022.00134
Lorenzo Rosa, Andrea Garbugli
Next-generation AI applications benefit from executing close to the network edge to better exploit co-locality to datasources and controlled actuators, and to meet stringent latency requirements. In the edge-enabled cloud continuum, time and safety-critical traffic coexists with best-effort flows, resulting in heterogeneous requirements that current networking middleware and frameworks struggle to support. This paper proposes INSANE, INtegrated Selective Acceleration at the Network Edge, the first edge-oriented middleware that integrates different network acceleration techniques (XDP, DPDK, RDMA, and TSN) within the same data distribution service. INSANE offers a uniform and simple interface, useful to support common data distribution patterns, that allow developers to exploit at runtime the most suitable network technology available in the dynamically determined deployment environment.
{"title":"Poster: INSANE – A Uniform Middleware API for Differentiated Quality using Heterogeneous Acceleration Techniques at the Network Edge","authors":"Lorenzo Rosa, Andrea Garbugli","doi":"10.1109/ICDCS54860.2022.00134","DOIUrl":"https://doi.org/10.1109/ICDCS54860.2022.00134","url":null,"abstract":"Next-generation AI applications benefit from executing close to the network edge to better exploit co-locality to datasources and controlled actuators, and to meet stringent latency requirements. In the edge-enabled cloud continuum, time and safety-critical traffic coexists with best-effort flows, resulting in heterogeneous requirements that current networking middleware and frameworks struggle to support. This paper proposes INSANE, INtegrated Selective Acceleration at the Network Edge, the first edge-oriented middleware that integrates different network acceleration techniques (XDP, DPDK, RDMA, and TSN) within the same data distribution service. INSANE offers a uniform and simple interface, useful to support common data distribution patterns, that allow developers to exploit at runtime the most suitable network technology available in the dynamically determined deployment environment.","PeriodicalId":225883,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)","volume":"303 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114841084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/ICDCS54860.2022.00078
Junmei Yao, H. Huang, Ruitao Xie, Xiaolong Zheng, Kaishun Wu
With the rapid growth of Internet of Things, the number of heterogeneous wireless devices working in the same frequency band increases dramatically, leading to severe cross-technology interference. To enable coexistence, researchers have proposed a large number of mechanisms to manage interference. However, existing mechanisms have severe modifications in either the physical or MAC (medium access control) layers, making them hard to be deployed on commercial devices. In this paper, we design and implement SledZig to boost cross-technology coexistence for low-power devices through both enabling more transmission opportunities and avoiding interference. SledZig is fully compatible with the standard in both physical and MAC layers. It decreases the WiFi signal power on the channel of low-power devices while keeps the WiFi transmission power unchanged, through making constellation points in the overlapped subcarriers have the lowest power, which can be achieved by just encoding the WiFi payload. We implement SledZig on hardware testbed and evaluate its performance under different settings. Experiment results show that SledZig can effectively increase ZigBee transmissions and improve its performance over a WiFi channel under various WiFi data traffic, with as low as 6.94% WiFi throughput loss.
{"title":"SledZig: Boosting Cross-Technology Coexistence for Low-Power Wireless Devices","authors":"Junmei Yao, H. Huang, Ruitao Xie, Xiaolong Zheng, Kaishun Wu","doi":"10.1109/ICDCS54860.2022.00078","DOIUrl":"https://doi.org/10.1109/ICDCS54860.2022.00078","url":null,"abstract":"With the rapid growth of Internet of Things, the number of heterogeneous wireless devices working in the same frequency band increases dramatically, leading to severe cross-technology interference. To enable coexistence, researchers have proposed a large number of mechanisms to manage interference. However, existing mechanisms have severe modifications in either the physical or MAC (medium access control) layers, making them hard to be deployed on commercial devices. In this paper, we design and implement SledZig to boost cross-technology coexistence for low-power devices through both enabling more transmission opportunities and avoiding interference. SledZig is fully compatible with the standard in both physical and MAC layers. It decreases the WiFi signal power on the channel of low-power devices while keeps the WiFi transmission power unchanged, through making constellation points in the overlapped subcarriers have the lowest power, which can be achieved by just encoding the WiFi payload. We implement SledZig on hardware testbed and evaluate its performance under different settings. Experiment results show that SledZig can effectively increase ZigBee transmissions and improve its performance over a WiFi channel under various WiFi data traffic, with as low as 6.94% WiFi throughput loss.","PeriodicalId":225883,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125326806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/ICDCS54860.2022.00080
Liwang Lu, Zhongjie Ba, Feng Lin, Jinsong Han, Kui Ren
Recent years have witnessed enormous research efforts on WiFi sensing to enable intelligent services of Internet of Things. However, due to the omni-directional broadcasting manner of WiFi signals, the activity semantic underlying the signals is leaked to adversaries for surveillance in all probability. To reveal the threat, this paper demonstrates ActListener, which could eavesdrop on user activities imperceptibly using a WiFi infrastructure in any location of user sensing area. The proposed attack requires no direct physical access to the victim user’s devices and prior knowledge of activity recognition model details and device locations. In particular, ActListener first detects the signal segment induced by each human activity, and estimates the locations of legitimate devices and the victim users relative to the adversary’s device for further signal modeling. Then, ActListener models propagating WiFi signals to construct the relationship between physical locations and received signals, and converts the eavesdropped signals to that by legitimate devices based on the models. Furthermore, a neural network-based generative model is designed to calibrate the converted signals for resisting noises in over-the-air WiFi signals. Experiments show ActListener achieves 88.4% average α-similarity on recovering originally signals from eavesdropped ones, and over 90% accuracy in activity recognition.
{"title":"ActListener: Imperceptible Activity Surveillance by Pervasive Wireless Infrastructures","authors":"Liwang Lu, Zhongjie Ba, Feng Lin, Jinsong Han, Kui Ren","doi":"10.1109/ICDCS54860.2022.00080","DOIUrl":"https://doi.org/10.1109/ICDCS54860.2022.00080","url":null,"abstract":"Recent years have witnessed enormous research efforts on WiFi sensing to enable intelligent services of Internet of Things. However, due to the omni-directional broadcasting manner of WiFi signals, the activity semantic underlying the signals is leaked to adversaries for surveillance in all probability. To reveal the threat, this paper demonstrates ActListener, which could eavesdrop on user activities imperceptibly using a WiFi infrastructure in any location of user sensing area. The proposed attack requires no direct physical access to the victim user’s devices and prior knowledge of activity recognition model details and device locations. In particular, ActListener first detects the signal segment induced by each human activity, and estimates the locations of legitimate devices and the victim users relative to the adversary’s device for further signal modeling. Then, ActListener models propagating WiFi signals to construct the relationship between physical locations and received signals, and converts the eavesdropped signals to that by legitimate devices based on the models. Furthermore, a neural network-based generative model is designed to calibrate the converted signals for resisting noises in over-the-air WiFi signals. Experiments show ActListener achieves 88.4% average α-similarity on recovering originally signals from eavesdropped ones, and over 90% accuracy in activity recognition.","PeriodicalId":225883,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129810835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/ICDCS54860.2022.00015
Tian Xie, Sanchal Thakkar, Ting He, P. Mcdaniel, Quinn K. Burke
In-network caching and flexible routing are two of the most celebrated advantages of next generation network infrastructures. Yet few solutions are available for jointly optimizing caching and routing that provide performance guarantees for an arbitrary topology. We take a holistic approach towards this fundamental problem by analyzing its complexity in all the cases and developing polynomial-time algorithms with approximation guarantees in important special cases. We also reveal the fundamental challenge in achieving guaranteed approximation in the general case and propose an alternating optimization algorithm with good performance and fast convergence. Our algorithms have demonstrated superior performance in both routing cost and congestion compared to the state-of-the-art solutions in evaluations based on real topology and request traces.
{"title":"Joint Caching and Routing in Cache Networks with Arbitrary Topology","authors":"Tian Xie, Sanchal Thakkar, Ting He, P. Mcdaniel, Quinn K. Burke","doi":"10.1109/ICDCS54860.2022.00015","DOIUrl":"https://doi.org/10.1109/ICDCS54860.2022.00015","url":null,"abstract":"In-network caching and flexible routing are two of the most celebrated advantages of next generation network infrastructures. Yet few solutions are available for jointly optimizing caching and routing that provide performance guarantees for an arbitrary topology. We take a holistic approach towards this fundamental problem by analyzing its complexity in all the cases and developing polynomial-time algorithms with approximation guarantees in important special cases. We also reveal the fundamental challenge in achieving guaranteed approximation in the general case and propose an alternating optimization algorithm with good performance and fast convergence. Our algorithms have demonstrated superior performance in both routing cost and congestion compared to the state-of-the-art solutions in evaluations based on real topology and request traces.","PeriodicalId":225883,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128721142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/cgo.2013.6494974
S. Nirenburg, T. Oates
Provides a listing of current committee members.
提供当前委员会成员的列表。
{"title":"Organizing committee","authors":"S. Nirenburg, T. Oates","doi":"10.1109/cgo.2013.6494974","DOIUrl":"https://doi.org/10.1109/cgo.2013.6494974","url":null,"abstract":"Provides a listing of current committee members.","PeriodicalId":225883,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126401811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/ICDCS54860.2022.00096
L. M. Bine, A. Boukerche, L. B. Ruiz, A. Loureiro
Internet of Drones (IoD) is an architecture that aims to enable different drones to share the same airspace. This architecture can help coordinate drone access to airspace in urban environments. Considering that the IoD is a dynamic network, it is possible to have scenarios in which drone traffic is sparse when, for instance, the network has isolated drones. In this case, the drones’ communication range does not reach any other drone. Thus, store-carry-forward protocols may be suitable for maintaining network communication. Moreover, different networks can collaborate to fill these communication gaps. In this study, we explore the collaboration between IoD and Bus Networks. Our analysis shows that maintaining a hybrid communication between drones and buses can fill the gaps in the communication between drones. The main goal of this work is to present the IoDSCF – a store-carry-forward routing protocol for joint Bus Networks and the Internet of Drones (IoD). IoDSCF takes advantage of both networks to extend the communication reachability. Our results reveal that IoDSCF presents better results in the number of delivered packets and end-to-end delay than a solution based only on communication between drones. This is a promising strategy for data communication, mainly in smart cities.
{"title":"IoDSCF: A Store-Carry-Forward Routing Protocol for joint Bus Networks and Internet of Drones","authors":"L. M. Bine, A. Boukerche, L. B. Ruiz, A. Loureiro","doi":"10.1109/ICDCS54860.2022.00096","DOIUrl":"https://doi.org/10.1109/ICDCS54860.2022.00096","url":null,"abstract":"Internet of Drones (IoD) is an architecture that aims to enable different drones to share the same airspace. This architecture can help coordinate drone access to airspace in urban environments. Considering that the IoD is a dynamic network, it is possible to have scenarios in which drone traffic is sparse when, for instance, the network has isolated drones. In this case, the drones’ communication range does not reach any other drone. Thus, store-carry-forward protocols may be suitable for maintaining network communication. Moreover, different networks can collaborate to fill these communication gaps. In this study, we explore the collaboration between IoD and Bus Networks. Our analysis shows that maintaining a hybrid communication between drones and buses can fill the gaps in the communication between drones. The main goal of this work is to present the IoDSCF – a store-carry-forward routing protocol for joint Bus Networks and the Internet of Drones (IoD). IoDSCF takes advantage of both networks to extend the communication reachability. Our results reveal that IoDSCF presents better results in the number of delivered packets and end-to-end delay than a solution based only on communication between drones. This is a promising strategy for data communication, mainly in smart cities.","PeriodicalId":225883,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114531930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Geo-replication is essential in reliable large-scale cloud applications. We argue that existing replication solutions are too rigid to support today’s diversity of data consistency and performance requirements. Stabilizer is a flexible geo-replication library, supporting user-defined consistency models. The library achieves high performance using control-plane / data-plane separation: control events do not disrupt data flow. Our API offers simple control-plane operators that allow an application to define its desired consistency model: a stability frontier predicate. We build a wide-area K/V store with Stabilizer, a Dropbox-like application, and a prototype pub/sub system to show its versatility and evaluate its performance. When compared with a Paxos-based consistency protocol in an emulated Amazon EC2 wide-area network, experiments show that for a scenario requiring a more accurate consistency model, Stabilizer achieves a 24.75% latency performance improvement. Compared to Apache Pulsar in a real WAN environment, Stabilizer’s dynamic reconfiguration mechanism improves the pub/sub system performance significantly according to our experiment results.
{"title":"Stabilizer: Geo-Replication with User-defined Consistency","authors":"Pengze Li, Lichen Pan, Xinzhe Yang, Weijia Song, Zhen Xiao, K. Birman","doi":"10.1109/ICDCS54860.2022.00042","DOIUrl":"https://doi.org/10.1109/ICDCS54860.2022.00042","url":null,"abstract":"Geo-replication is essential in reliable large-scale cloud applications. We argue that existing replication solutions are too rigid to support today’s diversity of data consistency and performance requirements. Stabilizer is a flexible geo-replication library, supporting user-defined consistency models. The library achieves high performance using control-plane / data-plane separation: control events do not disrupt data flow. Our API offers simple control-plane operators that allow an application to define its desired consistency model: a stability frontier predicate. We build a wide-area K/V store with Stabilizer, a Dropbox-like application, and a prototype pub/sub system to show its versatility and evaluate its performance. When compared with a Paxos-based consistency protocol in an emulated Amazon EC2 wide-area network, experiments show that for a scenario requiring a more accurate consistency model, Stabilizer achieves a 24.75% latency performance improvement. Compared to Apache Pulsar in a real WAN environment, Stabilizer’s dynamic reconfiguration mechanism improves the pub/sub system performance significantly according to our experiment results.","PeriodicalId":225883,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128429919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/ICDCS54860.2022.00038
Greg Cusack, Maziyar Nazari, Sepideh Goodarzy, Erika Hunhoff, Prerit Oberai, Eric Keller, Eric Rozner, Richard Han
This paper pushes the limits of automated resource allocation in container environments. Recent works set container CPU and memory limits by automatically scaling containers based on past resource usage. However, these systems are heavy- weight and run on coarse-grained time scales, resulting in poor performance when predictions are incorrect. We propose Escra, a container orchestrator that enables fine-grained, event- based resource allocation for a single container and distributed resource allocation to manage a collection of containers. Escra performs resource allocation on sub-second intervals within and across hosts, allowing operators to cost-effectively scale resources without performance penalty. We evaluate Escra on two types of containerized applications: microservices and serverless functions. In microservice environments, fine-grained and event- based resource allocation can reduce application latency by up to 96.9% and increase throughput by up to 3.2x when compared against the current state-of-the-art. Escra can increase performance while simultaneously reducing 50th and 99th%ile CPU waste by over 10x and 3.2x, respectively. In serverless environments, Escra can reduce CPU reservations by over 2.1x and memory reservations by more than 2x while maintaining similar end-to-end performance.
{"title":"Escra: Event-driven, Sub-second Container Resource Allocation","authors":"Greg Cusack, Maziyar Nazari, Sepideh Goodarzy, Erika Hunhoff, Prerit Oberai, Eric Keller, Eric Rozner, Richard Han","doi":"10.1109/ICDCS54860.2022.00038","DOIUrl":"https://doi.org/10.1109/ICDCS54860.2022.00038","url":null,"abstract":"This paper pushes the limits of automated resource allocation in container environments. Recent works set container CPU and memory limits by automatically scaling containers based on past resource usage. However, these systems are heavy- weight and run on coarse-grained time scales, resulting in poor performance when predictions are incorrect. We propose Escra, a container orchestrator that enables fine-grained, event- based resource allocation for a single container and distributed resource allocation to manage a collection of containers. Escra performs resource allocation on sub-second intervals within and across hosts, allowing operators to cost-effectively scale resources without performance penalty. We evaluate Escra on two types of containerized applications: microservices and serverless functions. In microservice environments, fine-grained and event- based resource allocation can reduce application latency by up to 96.9% and increase throughput by up to 3.2x when compared against the current state-of-the-art. Escra can increase performance while simultaneously reducing 50th and 99th%ile CPU waste by over 10x and 3.2x, respectively. In serverless environments, Escra can reduce CPU reservations by over 2.1x and memory reservations by more than 2x while maintaining similar end-to-end performance.","PeriodicalId":225883,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115988659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/ICDCS54860.2022.00125
Marcello Di Giammarco, F. Mercaldo, Fabio Martinelli, A. Santone
Often when we have a lot of data available we can not give them an interpretability and an explainability such as to be able to extract answers, and even more so diagnosis in the medical field. The aim of this contribution is to introduce a way to provide explainability to data and features that could escape even medical doctors, and that with the use of Machine Learning models can be categorized and "explained".
{"title":"Explainable Deep Learning Methodologies for Biomedical Images Classification","authors":"Marcello Di Giammarco, F. Mercaldo, Fabio Martinelli, A. Santone","doi":"10.1109/ICDCS54860.2022.00125","DOIUrl":"https://doi.org/10.1109/ICDCS54860.2022.00125","url":null,"abstract":"Often when we have a lot of data available we can not give them an interpretability and an explainability such as to be able to extract answers, and even more so diagnosis in the medical field. The aim of this contribution is to introduce a way to provide explainability to data and features that could escape even medical doctors, and that with the use of Machine Learning models can be categorized and \"explained\".","PeriodicalId":225883,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)","volume":"218 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114594774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Federated Learning (FL) suffers from Low-quality model training in mobile edge computing, due to the dynamic environment of mobile clients. To the best of our knowledge, most FL frameworks follow the reactive client scheduling, in which the FL parameter server selects participants according to the currently-observed state of clients. Thus, the participants selected by the reactive-manner methods are very likely to fail while training a round of FL. To this end, we propose a proactive Context-aware Federated Learning (ContextFL) mechanism, which consists of two primary modules. Firstly, the state prediction module enables each client device to predict the conditions of both local training and reporting phases of FL locally. Secondly, the decision-making algorithm module is devised using the contextual Multi-Armed Bandit (cMAB) framework, which can help the parameter server select the most appropriate group of mobile clients. Finally, we carried out trace-driven FL experiments using real-world mobility datasets collected from volunteers. The evaluation results demonstrate that the proposed ContextFL mechanism outperforms other baselines in terms of the convergence stability of the global FL model and the ratio of valid participants.
{"title":"ContextFL: Context-aware Federated Learning by Estimating the Training and Reporting Phases of Mobile Clients","authors":"Huawei Huang, Ruixin Li, Jialiang Liu, Sicong Zhou, Kangying Lin, Zibin Zheng","doi":"10.1109/ICDCS54860.2022.00061","DOIUrl":"https://doi.org/10.1109/ICDCS54860.2022.00061","url":null,"abstract":"Federated Learning (FL) suffers from Low-quality model training in mobile edge computing, due to the dynamic environment of mobile clients. To the best of our knowledge, most FL frameworks follow the reactive client scheduling, in which the FL parameter server selects participants according to the currently-observed state of clients. Thus, the participants selected by the reactive-manner methods are very likely to fail while training a round of FL. To this end, we propose a proactive Context-aware Federated Learning (ContextFL) mechanism, which consists of two primary modules. Firstly, the state prediction module enables each client device to predict the conditions of both local training and reporting phases of FL locally. Secondly, the decision-making algorithm module is devised using the contextual Multi-Armed Bandit (cMAB) framework, which can help the parameter server select the most appropriate group of mobile clients. Finally, we carried out trace-driven FL experiments using real-world mobility datasets collected from volunteers. The evaluation results demonstrate that the proposed ContextFL mechanism outperforms other baselines in terms of the convergence stability of the global FL model and the ratio of valid participants.","PeriodicalId":225883,"journal":{"name":"2022 IEEE 42nd International Conference on Distributed Computing Systems (ICDCS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126949674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：