Proceedings of the 2nd European Workshop on Machine Learning and Systems最新文献

筛选
英文 中文
syslrn
Proceedings of the 2nd European Workshop on Machine Learning and Systems Pub Date : 2022-04-05 DOI: 10.1145/3517207.3526979
D. Sanvito, G. Siracusano, Sharan Santhanam, R. González, Robert Bifulco
{"title":"syslrn","authors":"D. Sanvito, G. Siracusano, Sharan Santhanam, R. González, Robert Bifulco","doi":"10.1145/3517207.3526979","DOIUrl":"https://doi.org/10.1145/3517207.3526979","url":null,"abstract":"While monitoring system behavior to detect anomalies and failures is important, existing methods based on log-analysis can only be as good as the information contained in the logs, and other approaches that look at the OS-level software state introduce high overheads. We tackle the problem with syslrn, a system that first builds an understanding of a target system offline, and then tailors the online monitoring instrumentation based on the learned identifiers of normal behavior. While our syslrn prototype is still preliminary and lacks many features, we show in a case study for the monitoring of OpenStack failures that it can outperform state-of-the-art log-analysis systems with little overhead.","PeriodicalId":405533,"journal":{"name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124327508","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
FlexHTTP: an intelligent and scalable HTTP version selection system FlexHTTP:一个智能的、可扩展的HTTP版本选择系统
Proceedings of the 2nd European Workshop on Machine Learning and Systems Pub Date : 2022-04-05 DOI: 10.1145/3517207.3526972
Mengying Zhou, ZhengWu Li, Shihan Lin, Xin Wang, Yang Chen
{"title":"FlexHTTP: an intelligent and scalable HTTP version selection system","authors":"Mengying Zhou, ZhengWu Li, Shihan Lin, Xin Wang, Yang Chen","doi":"10.1145/3517207.3526972","DOIUrl":"https://doi.org/10.1145/3517207.3526972","url":null,"abstract":"HTTP has been the primary protocol for web data transmission for decades. Since the late 1990s, HTTP/1.1 has been widely used. Recently, both HTTP/2 and HTTP/3 have been proposed to achieve a better experience on web browsing. However, it is still unclear which of them performs better in different scenarios. In this paper, we first leverage the controllable experimental environment of the Emulab testbed to conduct a series of measurements and find that under different network conditions and web page structures, neither HTTP/2 nor HTTP/3 can always perform better. Motivated by this finding, we propose FlexHTTP, an intelligent and scalable HTTP version selection system. FlexHTTP embeds a supervised machine learning-based classifier to select the appropriate HTTP version according to network conditions and web page structures. FlexHTTP adopts a set of distributed agent servers to ensure scalability and keep the classifier up-to-date under network dynamics. We implement a proof-of-concept prototype of FlexHTTP on the Emulab testbed. Experiments show that FlexHTTP achieves a reduction of Speed Index by up to 600ms.","PeriodicalId":405533,"journal":{"name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124395199","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: 0
DyFiP
Proceedings of the 2nd European Workshop on Machine Learning and Systems Pub Date : 2022-04-05 DOI: 10.1145/3517207.3526982
Muhammad Sabih, Frank Hannig, Jürgen Teich
{"title":"DyFiP","authors":"Muhammad Sabih, Frank Hannig, Jürgen Teich","doi":"10.1145/3517207.3526982","DOIUrl":"https://doi.org/10.1145/3517207.3526982","url":null,"abstract":"Filter pruning is one of the most effective ways to accelerate Convolutional Neural Networks (CNNs). Most of the existing works are focused on the static pruning of CNN filters. In dynamic pruning of CNN filters, existing works are based on the idea of switching between different branches of a CNN or exiting early based on the hardness of a sample. These approaches can reduce the average latency of inference, but they cannot reduce the longest-path latency of inference. In contrast, we present a novel approach of dynamic filter pruning that utilizes explainable AI along with early coarse prediction in the intermediate layers of a CNN. This coarse prediction is performed using a simple branch that is trained to perform top-k classification. The branch either predicts the output class with high confidence, in which case the rest of the computations are left out. Alternatively, the branch predicts the output class to be within a subset of possible output classes. After this coarse prediction, only those filters that are important for this subset of classes are then evaluated. The importances of filters for each output class are obtained using explainable AI. Using this concept of dynamic pruning, we are able not only to reduce the average latency of inference, but also the longest-path latency of inference. Our proposed architecture for dynamic pruning can be deployed on different hardware platforms.","PeriodicalId":405533,"journal":{"name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122803513","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: 6
Efficient multiclass classification with duet 有效的二元多类分类
Proceedings of the 2nd European Workshop on Machine Learning and Systems Pub Date : 2022-04-05 DOI: 10.1145/3517207.3526970
S. Vargaftik, Y. Ben-Itzhak
{"title":"Efficient multiclass classification with duet","authors":"S. Vargaftik, Y. Ben-Itzhak","doi":"10.1145/3517207.3526970","DOIUrl":"https://doi.org/10.1145/3517207.3526970","url":null,"abstract":"In the upcoming era of edge computing, the capability to perform fast training and classification at the edge is an increasing need due to limited connectivity, hardware resources, privacy concerns, profitability, and more. Accordingly, we propose a new classifier termed Duet. Duet incorporates the advantages of bagging and boosting decision-tree-based ensemble methods (DTEMs) by using two classifiers instead of a monolithic one. A simple bagging model is trained using the entire training dataset and is responsible for capturing the easier concepts. Then, a boosting model is trained using only a fraction of the dataset representing the concepts the bagging model finds hard. To make the whole process resource efficient, we develop a new heuristic approach to rank data with respect to concepts that the bagging model finds hard. We use this approach, termed data instance predictability to determine the dataset fraction for the boosting model training. We implement Duet as a scikit-learn classifier. Evaluation using datasets from different domains and with different characteristics indicates that Duet offers a better tradeoff between classification accuracy and system performance than monolithic DTEMs. Moreover, in an evaluation over a resource-constrained Raspberry Pi 3 device Duet successfully completes all training tasks, where some monolithic models fail due to insufficient resources, indicating broader applicability of Duet to resource-constrained edge devices. Duet is a part of an effort for advancements in resource-efficient classification, and its scikit-learn implementation can be found in https://research.vmware.com/projects/efficient-machine-learning-classification.","PeriodicalId":405533,"journal":{"name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132348508","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: 0
Reinforcement learning for resource management in multi-tenant serverless platforms 多租户无服务器平台中资源管理的强化学习
Proceedings of the 2nd European Workshop on Machine Learning and Systems Pub Date : 2022-04-05 DOI: 10.1145/3517207.3526971
Haoran Qiu, Weichao Mao, Archit Patke, Chen Wang, H. Franke, Z. Kalbarczyk, T. Başar, R. Iyer
{"title":"Reinforcement learning for resource management in multi-tenant serverless platforms","authors":"Haoran Qiu, Weichao Mao, Archit Patke, Chen Wang, H. Franke, Z. Kalbarczyk, T. Başar, R. Iyer","doi":"10.1145/3517207.3526971","DOIUrl":"https://doi.org/10.1145/3517207.3526971","url":null,"abstract":"Serverless Function-as-a-Service (FaaS) is an emerging cloud computing paradigm that frees application developers from infrastructure management tasks such as resource provisioning and scaling. To reduce the tail latency of functions and improve resource utilization, recent research has been focused on applying online learning algorithms such as reinforcement learning (RL) to manage resources. Compared to existing heuristics-based resource management approaches, RL-based approaches eliminate humans in the loop and avoid the painstaking generation of heuristics. In this paper, we show that the state-of-the-art single-agent RL algorithm (S-RL) suffers up to 4.6x higher function tail latency degradation on multi-tenant serverless FaaS platforms and is unable to converge during training. We then propose and implement a customized multi-agent RL algorithm based on Proximal Policy Optimization, i.e., multi-agent PPO (MA-PPO). We show that in multi-tenant environments, MA-PPO enables each agent to be trained until convergence and provides online performance comparable to S-RL in single-tenant cases with less than 10% degradation. Besides, MA-PPO provides a 4.4x improvement in S-RL performance (in terms of function tail latency) in multi-tenant cases.","PeriodicalId":405533,"journal":{"name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127690536","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: 9
Live video analytics as a service 实时视频分析服务
Proceedings of the 2nd European Workshop on Machine Learning and Systems Pub Date : 2022-04-05 DOI: 10.1145/3517207.3526973
G. H. Apostolo, P. Bauszat, Vinod Nigade, H. Bal, Lin Wang
{"title":"Live video analytics as a service","authors":"G. H. Apostolo, P. Bauszat, Vinod Nigade, H. Bal, Lin Wang","doi":"10.1145/3517207.3526973","DOIUrl":"https://doi.org/10.1145/3517207.3526973","url":null,"abstract":"Many private and public organizations deploy large numbers of cameras, which are used in application services for public safety, healthcare, and traffic control. Recent advances in deep learning have demonstrated remarkable accuracy on computer analytics tasks that are fundamental for these applications, such as object detection and action recognition. While deep learning opens the door for the automation of camera-based applications, deploying pipelines for live video analytics is still a complicated process that requires domain expertise in the fields of machine learning, computer vision, computer systems, and networks. The problem is further amplified when multiple pipelines need to be deployed on the same infrastructure to meet different users' diverse and yet dynamic needs. In this paper, we present a live-video-analytics-as-a-service vision, aiming to remove the complexity barrier and achieve flexibility, agility, and efficiency for applications based on live video analytics. We motivate our vision by identifying its requirements and the shortcomings of existing approaches. Based on our analysis, we present our envisioned system design and discuss the challenges that need to be addressed to make it a reality.","PeriodicalId":405533,"journal":{"name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127891715","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: 1
Empirical analysis of federated learning in heterogeneous environments 异构环境下联邦学习的实证分析
Proceedings of the 2nd European Workshop on Machine Learning and Systems Pub Date : 2022-04-05 DOI: 10.1145/3517207.3526969
A. Abdelmoniem, Chen-Yu Ho, Pantelis Papageorgiou, M. Canini
{"title":"Empirical analysis of federated learning in heterogeneous environments","authors":"A. Abdelmoniem, Chen-Yu Ho, Pantelis Papageorgiou, M. Canini","doi":"10.1145/3517207.3526969","DOIUrl":"https://doi.org/10.1145/3517207.3526969","url":null,"abstract":"Federated learning (FL) is becoming a popular paradigm for collaborative learning over distributed, private datasets owned by non-trusting entities. FL has seen successful deployment in production environments, and it has been adopted in services such as virtual keyboards, auto-completion, item recommendation, and several IoT applications. However, FL comes with the challenge of performing training over largely heterogeneous datasets, devices, and networks that are out of the control of the centralized FL server. Motivated by this inherent setting, we make a first step towards characterizing the impact of device and behavioral heterogeneity on the trained model. We conduct an extensive empirical study spanning close to 1.5K unique configurations on five popular FL benchmarks. Our analysis shows that these sources of heterogeneity have a major impact on both model performance and fairness, thus shedding light on the importance of considering heterogeneity in FL system design.","PeriodicalId":405533,"journal":{"name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134218402","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: 16
Deep learning on microcontrollers: a study on deployment costs and challenges 微控制器上的深度学习:部署成本和挑战的研究
Proceedings of the 2nd European Workshop on Machine Learning and Systems Pub Date : 2022-04-05 DOI: 10.1145/3517207.3526978
F. Svoboda, J. Fernández-Marqués, Edgar Liberis, N. Lane
{"title":"Deep learning on microcontrollers: a study on deployment costs and challenges","authors":"F. Svoboda, J. Fernández-Marqués, Edgar Liberis, N. Lane","doi":"10.1145/3517207.3526978","DOIUrl":"https://doi.org/10.1145/3517207.3526978","url":null,"abstract":"Microcontrollers are an attractive deployment target due to their low cost, modest power usage and abundance in the wild. However, deploying models to such hardware is non-trivial due to a small amount of on-chip RAM (often < 512KB) and limited compute capabilities. In this work, we delve into the requirements and challenges of fast DNN inference on MCUs: we describe how the memory hierarchy influences the architecture of the model, expose often under-reported costs of compression and quantization techniques, and highlight issues that become critical when deploying to MCUs compared to mobiles. Our findings and experiences are also distilled into a set of guidelines that should ease the future deployment of DNN-based applications on microcontrollers.","PeriodicalId":405533,"journal":{"name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131504860","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
dSyncPS
Proceedings of the 2nd European Workshop on Machine Learning and Systems Pub Date : 2022-04-05 DOI: 10.1145/3517207.3526981
Yibo Guo, Andrew E. Wang
{"title":"dSyncPS","authors":"Yibo Guo, Andrew E. Wang","doi":"10.1145/3517207.3526981","DOIUrl":"https://doi.org/10.1145/3517207.3526981","url":null,"abstract":"The increasing demand of applying machine learning technologies in various domains has driven the involvement of complex machine learning models. To fulfill this demand, distributed machine learning has become the de facto standard computing paradigm for model training. Machine-Learning-as-a-Service (MLaaS) has also emerged as a solution provided by cloud service providers to address this need. With MLaaS, customers can submit their models and training datasets to the service providers, and leverage the existing cloud infrastructure for model training and inference. However, we find that, for end users who require complex and accurate machine learning models but only obtains moderate amount of data, existing solutions are insufficient. The main issue is the lack of support for dynamic deployment of distributed machine learning tasks. To address this issue, we propose a parameter server based framework, called dSyncPS, that allows worker nodes to participate in training dynamically. The key idea is that it separates parameter synchronization from aggregation function in the parameter server nodes, thus resulting in a delayed synchrony.","PeriodicalId":405533,"journal":{"name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","volume":"266 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114014247","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: 0
Scaling knowledge graph embedding models for link prediction 链接预测的缩放知识图嵌入模型
Proceedings of the 2nd European Workshop on Machine Learning and Systems Pub Date : 2022-01-08 DOI: 10.1145/3517207.3526974
Nasrullah Sheikh, Xiao Qin, B. Reinwald, Chuan Lei
{"title":"Scaling knowledge graph embedding models for link prediction","authors":"Nasrullah Sheikh, Xiao Qin, B. Reinwald, Chuan Lei","doi":"10.1145/3517207.3526974","DOIUrl":"https://doi.org/10.1145/3517207.3526974","url":null,"abstract":"Developing scalable solutions for training Graph Neural Networks (GNNs) for link prediction tasks is challenging due to the inherent data dependencies which entail high computational costs and a huge memory footprint. We propose a new method for scaling training of knowledge graph embedding models for link prediction to address these challenges. Towards this end, we propose the following algorithmic strategies: self-sufficient partitions, constraint-based negative sampling, and edge mini-batch training. The experimental evaluation shows that our scaling solution for GNN-based knowledge graph embedding models achieves a 16x speed up on benchmark datasets while maintaining a comparable model performance to non-distributed methods on standard metrics.","PeriodicalId":405533,"journal":{"name":"Proceedings of the 2nd European Workshop on Machine Learning and Systems","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129335629","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书