User-centric Composable Services: A New Generation of Personal Data Analytics
This addresses the problem of inefficient personal data analytics for individual users by enabling user-centric composable services, though it appears incremental as it builds on existing edge computing trends.
The paper tackles the gap between current ML systems focused on model performance and user needs for response time and expressiveness by proposing the Zoo system, built on Owl, to support ML model construction, composition, and deployment on edge and local devices.
Machine Learning (ML) techniques, such as Neural Network, are widely used in today's applications. However, there is still a big gap between the current ML systems and users' requirements. ML systems focus on improving the performance of models in training, while individual users cares more about response time and expressiveness of the tool. Many existing research and product begin to move computation towards edge devices. Based on the numerical computing system Owl, we propose to build the Zoo system to support construction, compose, and deployment of ML models on edge and local devices.