User-centric Composable Services: A New Generation of Personal Data Analytics

TL;DR

This paper introduces Zoo, a system built on Owl, enabling users to construct, compose, and deploy machine learning models on edge and local devices, addressing user-centric needs like response time and expressiveness.

Contribution

The paper presents Zoo, a novel system that enhances user-centric ML model deployment on edge devices, bridging the gap between system performance and user requirements.

Findings

Zoo supports efficient model construction and deployment on edge devices.

The system improves response time and expressiveness for end-users.

Empirical evaluation shows Zoo's effectiveness in real-world scenarios.

Abstract

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.