اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدServerless Model Serving for Data Science
290
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Machine learning (ML) is an important part of modern data science applications. Data scientists today have to manage the end-to-end ML life cycle that includes both model training and model serving, the latter of which is essential, as it makes their works available to end-users. Systems for model serving require high performance, low cost, and ease of management. Cloud providers are already offering model serving options, including managed services and self-rented servers. Recently, serverless computing, whose advantages include high elasticity and fine-grained cost model, brings another possibility for model serving. In this paper, we study the viability of serverless as a mainstream model serving platform for data science applications. We conduct a comprehensive evaluation of the performance and cost of serverless against other model serving systems on two clouds: Amazon Web Service (AWS) and Google Cloud Platform (GCP). We find that serverless outperforms many cloud-based alternatives with respect to cost and performance. More interestingly, under some circumstances, it can even outperform GPU-based systems for both average latency and cost. These results are different from previous works claim that serverless is not suitable for model serving, and are contrary to the conventional wisdom that GPU-based systems are better for ML workloads than CPU-based systems. Other findings include a large gap in cold start time between AWS and GCP serverless functions, and serverless low sensitivity to changes in workloads or models. Our evaluation results indicate that serverless is a viable option for model serving. Finally, we present several practical recommendations for data scientists on how to use serverless for scalable and cost-effective model serving.
قيم البحث
اقرأ أيضاً
Data-intensive applications are becoming commonplace in all science disciplines. They are comprised of a rich set of sub-domains such as data engineering, deep learning, and machine learning. These applications are built around efficient data abstrac
tions and operators that suit the applications of different domains. Often lack of a clear definition of data structures and operators in the field has led to other implementations that do not work well together. The HPTMT architecture that we proposed recently, identifies a set of data structures, operators, and an execution model for creating rich data applications that links all aspects of data engineering and data science together efficiently. This paper elaborates and illustrates this architecture using an end-to-end application with deep learning and data engineering parts working together.
We present status and results of AstroGrid-D, a joint effort of astrophysicists and computer scientists to employ grid technology for scientific applications. AstroGrid-D provides access to a network of distributed machines with a set of commands as
well as software interfaces. It allows simple use of computer and storage facilities and to schedule or monitor compute tasks and data management. It is based on the Globus Toolkit middleware (GT4). Chapter 1 describes the context which led to the demand for advanced software solutions in Astrophysics, and we state the goals of the project. We then present characteristic astrophysical applications that have been implemented on AstroGrid-D in chapter 2. We describe simulations of different complexity, compute-intensive calculations running on multiple sites, and advanced applications for specific scientific purposes, such as a connection to robotic telescopes. We can show from these examples how grid execution improves e.g. the scientific workflow. Chapter 3 explains the software tools and services that we adapted or newly developed. Section 3.1 is focused on the administrative aspects of the infrastructure, to manage users and monitor activity. Section 3.2 characterises the central components of our architecture: The AstroGrid-D information service to collect and store metadata, a file management system, the data management system, and a job manager for automatic submission of compute tasks. We summarise the successfully established infrastructure in chapter 4, concluding with our future plans to establish AstroGrid-D as a platform of modern e-Astronomy.
Despite existing work in machine learning inference serving, ease-of-use and cost efficiency remain challenges at large scales. Developers must manually search through thousands of model-variants
DNN-based video analytics have empowered many new applications (e.g., automated retail). Meanwhile, the proliferation of fog devices provides developers with more design options to improve performance and save cost. To the best of our knowledge, this
paper presents the first serverless system that takes full advantage of the client-fog-cloud synergy to better serve the DNN-based video analytics. Specifically, the system aims to achieve two goals: 1) Provide the optimal analytics results under the constraints of lower bandwidth usage and shorter round-trip time (RTT) by judiciously managing the computational and bandwidth resources deployed in the client, fog, and cloud environment. 2) Free developers from tedious administration and operation tasks, including DNN deployment, cloud and fogs resource management. To this end, we implement a holistic cloud-fog system referred to as VPaaS (Video-Platform-as-a-Service). VPaaS adopts serverless computing to enable developers to build a video analytics pipeline by simply programming a set of functions (e.g., model inference), which are then orchestrated to process videos through carefully designed modules. To save bandwidth and reduce RTT, VPaaS provides a new video streaming protocol that only sends low-quality video to the cloud. The state-of-the-art (SOTA) DNNs deployed at the cloud can identify regions of video frames that need further processing at the fog ends. At the fog ends, misidentified labels in these regions can be corrected using a light-weight DNN model. To address the data drift issues, we incorporate limited human feedback into the system to verify the results and adopt incremental learning to improve our system continuously. The evaluation demonstrates that VPaaS is superior to several SOTA systems: it maintains high accuracy while reducing bandwidth usage by up to 21%, RTT by up to 62.5%, and cloud monetary cost by up to 50%.
Cloud-based enterprise search services (e.g., Amazon Kendra) are enchanting to big data owners by providing them with convenient search solutions over their enterprise big datasets. However, individuals and businesses that deal with confidential big
data (eg, credential documents) are reluctant to fully embrace such services, due to valid concerns about data privacy. Solutions based on client-side encryption have been explored to mitigate privacy concerns. Nonetheless, such solutions hinder data processing, specifically clustering, which is pivotal in dealing with different forms of big data. For instance, clustering is critical to limit the search space and perform real-time search operations on big datasets. To overcome the hindrance in clustering encrypted big data, we propose privacy-preserving clustering schemes for three forms of unstructured encrypted big datasets, namely static, semi-dynamic, and dynamic datasets. To preserve data privacy, the proposed clustering schemes function based on statistical characteristics of the data and determine (A) the suitable number of clusters and (B) appropriate content for each cluster. Experimental results obtained from evaluating the clustering schemes on three different datasets demonstrate between 30% to 60% improvement on the clusters coherency compared to other clustering schemes for encrypted data. Employing the clustering schemes in a privacy-preserving enterprise search system decreases its search time by up to 78%, while increases the search accuracy by up to 35%.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
