IEEE INFOCOM 2021 - IEEE Conference on Computer Communications最新文献_第5页

Learning for Learning: Predictive Online Control of Federated Learning with Edge Provisioning 为学习而学习:基于边缘供应的联邦学习的预测在线控制

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Pub Date : 2021-05-10 DOI: 10.1109/INFOCOM42981.2021.9488733

Yibo Jin, Lei Jiao, Zhuzhong Qian, Sheng Zhang, Sanglu Lu

{"title":"Learning for Learning: Predictive Online Control of Federated Learning with Edge Provisioning","authors":"Yibo Jin, Lei Jiao, Zhuzhong Qian, Sheng Zhang, Sanglu Lu","doi":"10.1109/INFOCOM42981.2021.9488733","DOIUrl":"https://doi.org/10.1109/INFOCOM42981.2021.9488733","url":null,"abstract":"Operating federated learning optimally over distributed cloud-edge networks is a non-trivial task, which requires to manage data transference from user devices to edges, resource provisioning at edges, and federated learning between edges and the cloud. We formulate a non-linear mixed integer program, minimizing the long-term cumulative cost of such a federated learning system while guaranteeing the desired convergence of the machine learning models being trained. We then design a set of novel polynomial-time online algorithms to make adaptive decisions by solving continuous solutions and converting them to integers to control the system on the fly, based only on the predicted inputs about the dynamic and uncertain cloud-edge environments via online learning. We rigorously prove the competitive ratio, capturing the multiplicative gap between our approach using predicted inputs and the offline optimum using actual inputs. Extensive evaluations with real-world training datasets and system parameters confirm the empirical superiority of our approach over multiple state-of-the-art algorithms.","PeriodicalId":293079,"journal":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123299478","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}

引用次数: 12

NetMARKS: Network Metrics-AwaRe Kubernetes Scheduler Powered by Service Mesh NetMARKS:基于服务网格的Kubernetes调度器

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Pub Date : 2021-05-10 DOI: 10.1109/INFOCOM42981.2021.9488670

Lukasz Wojciechowski, Krzysztof Opasiak, Jakub Latusek, Maciej Wereski, Victor Morales, Taewan Kim, Moonki Hong

{"title":"NetMARKS: Network Metrics-AwaRe Kubernetes Scheduler Powered by Service Mesh","authors":"Lukasz Wojciechowski, Krzysztof Opasiak, Jakub Latusek, Maciej Wereski, Victor Morales, Taewan Kim, Moonki Hong","doi":"10.1109/INFOCOM42981.2021.9488670","DOIUrl":"https://doi.org/10.1109/INFOCOM42981.2021.9488670","url":null,"abstract":"Container technology has revolutionized the way software is being packaged and run. The telecommunications industry, now challenged with the 5G transformation, views containers as the best way to achieve agile infrastructure that can serve as a stable base for high throughput and low latency for 5G edge applications. These challenges make optimal scheduling of performance-sensitive containerized workflows a matter of emerging importance. Meanwhile, the wide adoption of Kubernetes across industries has placed it as a de-facto standard for container orchestration. Several attempts have been made to improve Kubernetes scheduling, but the existing solutions either do not respect current scheduling rules or only considered a static infrastructure viewpoint.To address this, we propose NetMARKS - a novel approach to Kubernetes pod scheduling that uses dynamic network metrics collected with Istio Service Mesh. This solution improves Kubernetes scheduling while being fully backward compatible. We validated our solution using different workloads and processing layouts. Based on our analysis, NetMARKS can reduce application response time up to 37 percent and save up to 50 percent of inter-node bandwidth in a fully automated manner. This significant improvement is crucial to Kubernetes adoption in 5G use cases, especially for multi-access edge computing and machine-to-machine communication.","PeriodicalId":293079,"journal":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124747410","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}

引用次数: 29

Crowdsourcing System for Numerical Tasks based on Latent Topic Aware Worker Reliability 基于潜在主题感知工作者可靠性的数字任务众包系统

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Pub Date : 2021-05-10 DOI: 10.1109/INFOCOM42981.2021.9488748

Zhuan Shi, Shanyang Jiang, Lan Zhang, Yang Du, Xiangyang Li

{"title":"Crowdsourcing System for Numerical Tasks based on Latent Topic Aware Worker Reliability","authors":"Zhuan Shi, Shanyang Jiang, Lan Zhang, Yang Du, Xiangyang Li","doi":"10.1109/INFOCOM42981.2021.9488748","DOIUrl":"https://doi.org/10.1109/INFOCOM42981.2021.9488748","url":null,"abstract":"Crowdsourcing is a widely adopted way for various labor-intensive tasks. One of the core problems in crowdsourcing systems is how to assign tasks to most suitable workers for better results, which heavily relies on the accurate profiling of each worker’s reliability for different topics of tasks. Many previous work have studied worker reliability for either explicit topics represented by task descriptions or latent topics for categorical tasks. In this work, we aim to accurately estimate more fine-grained worker reliability for latent topics in numerical tasks, so as to further improve the result quality. We propose a bayesian probabilistic model named Gaussian Latent Topic Model(GLTM) to mine the latent topics of numerical tasks based on workers’ behaviors and to estimate workers’ topic-level reliability. By utilizing the GLTM, we propose a truth inference algorithm named TI-GLTM to accurately infer the tasks’ truth and topics simultaneously and dynamically update workers’ topic-level reliability. We also design an online task assignment mechanism called MRA-GLTM, which assigns appropriate tasks to workers with the Maximum Reduced Ambiguity principle. The experiment results show our algorithms can achieve significantly lower MAE and MSE than that of the state-of-the-art approaches.","PeriodicalId":293079,"journal":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122167029","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}

引用次数: 8

VideoLoc: Video-based Indoor Localization with Text Information VideoLoc:基于视频的室内文本信息定位

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Pub Date : 2021-05-10 DOI: 10.1109/INFOCOM42981.2021.9488739

Shusheng Li, Wenbo He

{"title":"VideoLoc: Video-based Indoor Localization with Text Information","authors":"Shusheng Li, Wenbo He","doi":"10.1109/INFOCOM42981.2021.9488739","DOIUrl":"https://doi.org/10.1109/INFOCOM42981.2021.9488739","url":null,"abstract":"Indoor localization serves an important role in various scenarios such as navigation in shopping malls or hospitals. However, the existing technology is usually based on additional deployment and the signals suffer from strong environmental interference in the complex indoor environment. In this paper, we propose video-based indoor localization with text information (i.e. \"VideoLoc\") without the deployment of additional equipment. Videos taken by the phone carriers cover more critical information (e.g. logos in malls), while a single photo may fail to capture it. To reduce redundant information in the video, we propose key-frame selection based on deep learning model and clustering algorithm. Video frames are characterized with deep visual descriptors and the clustering algorithm efficiently clusters these descriptors into a set of non-overlapping snippets. We select keyframes from these non-overlapping snippets in terms of the cluster centroid that represents each snippet. Then, we propose text detection and recognition with the perspective transformation to make full use of stable and discriminative text information (e.g. logos or room numbers) in keyframes for localization. Finally, we obtain the location of the phone carrier via the triangulation algorithm. The experimental results show that VideoLoc achieves high precision of localization and is robust to dynamic environments.","PeriodicalId":293079,"journal":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123833579","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}

引用次数: 2

Bandit Learning with Predicted Context: Regret Analysis and Selective Context Query 具有预测上下文的强盗学习:后悔分析和选择性上下文查询

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Pub Date : 2021-05-10 DOI: 10.1109/INFOCOM42981.2021.9488896

Jianyi Yang, Shaolei Ren

{"title":"Bandit Learning with Predicted Context: Regret Analysis and Selective Context Query","authors":"Jianyi Yang, Shaolei Ren","doi":"10.1109/INFOCOM42981.2021.9488896","DOIUrl":"https://doi.org/10.1109/INFOCOM42981.2021.9488896","url":null,"abstract":"Contextual bandit learning selects actions (i.e., arms) based on context information to maximize rewards while balancing exploitation and exploration. In many applications (e.g., cloud resource management with dynamic workloads), before arm selection, the agent/learner can either predict context information online based on context history or selectively query the context from an outside expert. Motivated by this practical consideration, we study a novel contextual bandit setting where context information is either predicted online or queried from an expert. First, considering predicted context only, we quantify the impact of context prediction on the cumulative regret (compared to an oracle with perfect context information) by deriving an upper bound on regret, which takes the form of a weighted combination of regret incurred by standard bandit learning and the context prediction error. Then, inspired by the regret’s structural decomposition, we propose context query algorithms to selectively obtain outside expert’s input (subject to a total query budget) for more accurate context, decreasing the overall regret. Finally, we apply our algorithms to virtual machine scheduling on cloud platforms. The simulation results validate our regret analysis and shows the effectiveness of our selective context query algorithms.","PeriodicalId":293079,"journal":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123885755","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}

引用次数: 5

Owl: Congestion Control with Partially Invisible Networks via Reinforcement Learning Owl:通过强化学习实现部分不可见网络的拥塞控制

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Pub Date : 2021-05-10 DOI: 10.1109/INFOCOM42981.2021.9488851

Alessio Sacco, Matteo Flocco, Flavio Esposito, G. Marchetto

引用次数: 19

Modeling the Cost of Flexibility in Communication Networks 通信网络中灵活性成本的建模

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Pub Date : 2021-05-10 DOI: 10.1109/INFOCOM42981.2021.9488900

Alberto Martínez Alba, P. Babarczi, Andreas Blenk, Mu He, Patrick Kalmbach, Johannes Zerwas, W. Kellerer

引用次数: 6

DC2: Delay-aware Compression Control for Distributed Machine Learning 分布式机器学习的延迟感知压缩控制

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Pub Date : 2021-05-10 DOI: 10.1109/INFOCOM42981.2021.9488810

A. Abdelmoniem, M. Canini

{"title":"DC2: Delay-aware Compression Control for Distributed Machine Learning","authors":"A. Abdelmoniem, M. Canini","doi":"10.1109/INFOCOM42981.2021.9488810","DOIUrl":"https://doi.org/10.1109/INFOCOM42981.2021.9488810","url":null,"abstract":"Distributed training performs data-parallel training of DNN models which is a necessity for increasingly complex models and large datasets. Recent works are identifying major communication bottlenecks in distributed training. These works seek possible opportunities to speed-up the training in systems supporting distributed ML workloads. As communication reduction, compression techniques are proposed to speed up this communication phase. However, compression comes at the cost of reduced model accuracy, especially when compression is applied arbitrarily. Instead, we advocate a more controlled use of compression and propose DC2, a delay-aware compression control mechanism. DC2 couples compression control and network delays in applying compression adaptively. DC2 not only compensates for network variations but can also strike a better trade-off between training speed and accuracy. DC2 is implemented as a drop-in module to the communication library used by the ML toolkit and can operate in a variety of network settings. We empirically evaluate DC2 in network environments exhibiting low and high delay variations. Our evaluation of different popular CNN models and datasets shows that DC2 improves training speed-ups of up to 41× and 5.3 × over baselines with no-compression and uniform compression, respectively.","PeriodicalId":293079,"journal":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130777941","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}

引用次数: 23

6GAN: IPv6 Multi-Pattern Target Generation via Generative Adversarial Nets with Reinforcement Learning 基于强化学习的生成对抗网络的IPv6多模式目标生成

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Pub Date : 2021-05-10 DOI: 10.1109/INFOCOM42981.2021.9488912

Tianyu Cui, Gaopeng Gou, G. Xiong, Chang Liu, Peipei Fu, Zhen Li

{"title":"6GAN: IPv6 Multi-Pattern Target Generation via Generative Adversarial Nets with Reinforcement Learning","authors":"Tianyu Cui, Gaopeng Gou, G. Xiong, Chang Liu, Peipei Fu, Zhen Li","doi":"10.1109/INFOCOM42981.2021.9488912","DOIUrl":"https://doi.org/10.1109/INFOCOM42981.2021.9488912","url":null,"abstract":"Global IPv6 scanning has always been a challenge for researchers because of the limited network speed and computational power. Target generation algorithms are recently proposed to overcome the problem for Internet assessments by predicting a candidate set to scan. However, IPv6 custom address configuration emerges diverse addressing patterns discouraging algorithmic inference. Widespread IPv6 alias could also mislead the algorithm to discover aliased regions rather than valid host targets. In this paper, we introduce 6GAN, a novel architecture built with Generative Adversarial Net (GAN) and reinforcement learning for multi-pattern target generation. 6GAN forces multiple generators to train with a multi-class discriminator and an alias detector to generate non-aliased active targets with different addressing pattern types. The rewards from the discriminator and the alias detector help supervise the address sequence decision-making process. After adversarial training, 6GAN’s generators could keep a strong imitating ability for each pattern and 6GAN’s discriminator obtains outstanding pattern discrimination ability with a 0.966 accuracy. Experiments indicate that our work outperformed the state-of-the-art target generation algorithms by reaching a higher-quality candidate set.","PeriodicalId":293079,"journal":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131384002","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}

引用次数: 13

Mobile Crowdsensing for Data Freshness: A Deep Reinforcement Learning Approach 移动人群感知数据新鲜度:一种深度强化学习方法

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Pub Date : 2021-05-10 DOI: 10.1109/INFOCOM42981.2021.9488791

Zipeng Dai, Hao Wang, C. Liu, Rui Han, Jian Tang, Guoren Wang

{"title":"Mobile Crowdsensing for Data Freshness: A Deep Reinforcement Learning Approach","authors":"Zipeng Dai, Hao Wang, C. Liu, Rui Han, Jian Tang, Guoren Wang","doi":"10.1109/INFOCOM42981.2021.9488791","DOIUrl":"https://doi.org/10.1109/INFOCOM42981.2021.9488791","url":null,"abstract":"Data collection by mobile crowdsensing (MCS) is emerging as data sources for smart city applications, however how to ensure data freshness has sparse research exposure but quite important in practice. In this paper, we consider to use a group of mobile agents (MAs) like UAVs and driverless cars which are equipped with multiple antennas to move around in the task area to collect data from deployed sensor nodes (SNs). Our goal is to minimize the age of information (AoI) of all SNs and energy consumption of MAs during movement and data upload. To this end, we propose a centralized deep reinforcement learning (DRL)-based solution called \"DRL-freshMCS\" for controlling MA trajectory planning and SN scheduling. We further utilize implicit quantile networks to maintain the accurate value estimation and steady policies for MAs. Then, we design an exploration and exploitation mechanism by dynamic distributed prioritized experience replay. We also derive the theoretical lower bound for episodic AoI. Extensive simulation results show that DRL-freshMCS significantly reduces the episodic AoI per remaining energy, compared to five baselines when varying different number of antennas and data upload thresholds, and number of SNs. We also visualize their trajectories and AoI update process for clear illustrations.","PeriodicalId":293079,"journal":{"name":"IEEE INFOCOM 2021 - IEEE Conference on Computer Communications","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130172262","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}

引用次数: 12