Edge Learning with Timeliness Constraints: Challenges and Solutions

TL;DR

This paper addresses the challenges of achieving timely and accurate machine learning at the edge by proposing solutions for data, model, and resource management to meet strict delay constraints.

Contribution

It introduces the concept of timely edge learning, emphasizing total training delay, and proposes compression, scheduling, and pruning strategies for both training and inference.

Findings

Improved training accuracy within delay budgets

Enhanced inference completion ratios within deadlines

Effective data and model compression techniques

Abstract

Future machine learning (ML) powered applications, such as autonomous driving and augmented reality, involve training and inference tasks with timeliness requirements and are communication and computation intensive, which demands for the edge learning framework. The real-time requirements drive us to go beyond accuracy for ML. In this article, we introduce the concept of timely edge learning, aiming to achieve accurate training and inference while minimizing the communication and computation delay. We discuss key challenges and propose corresponding solutions from data, model and resource management perspectives to meet the timeliness requirements. Particularly, for edge training, we argue that the total training delay rather than rounds should be considered, and propose data or model compression, and joint device scheduling and resource management schemes for both centralized training and federated learning systems. For edge inference, we explore the dependency between accuracy and delay for communication and computation, and propose dynamic data compression and flexible pruning schemes. Two case studies show that the timeliness performances, including the training accuracy under a given delay budget and the completion ratio of inference tasks within deadline, are highly improved with the proposed solutions.