Serverless Data Science - Are We There Yet? A Case Study of Model Serving
Yuncheng Wu, Tien Tuan Anh Dinh, Guoyu Hu, Meihui Zhang, Yeow Meng Chee, Beng Chin Ooi
2022Proceedings of the 2022 International Conference on Management of Data25 citationsDOIOpen Access PDF
Abstract
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 of model serving require high performance, low cost, and ease of management. Cloud providers are already offering model serving choices, including managed services and self-rented servers. Recently, serverless computing, whose advantages include high elasticity and a fine-grained cost model, brings another option for model serving.
Topics & Concepts
Computer scienceServerCloud computingElasticity (physics)Data modelingData scienceDistributed computingWorld Wide WebDatabaseOperating systemMaterials scienceComposite materialCloud Computing and Resource ManagementIoT and Edge/Fog ComputingAdvanced Data Storage Technologies