Complexity-aware Adaptive Training and Inference for Edge-Cloud Distributed AI Systems

Abstract

The ubiquitous use of IoT and machine learning applications is creating large amounts of data that require accurate and real-time processing. Although edge-based smart data processing can be enabled by deploying pretrained models, the energy and memory constraints of edge devices necessitate distributed deep learning between the edge and the cloud for complex data. In this paper, we propose a distributed AI system to exploit both the edge and the cloud for training and inference. We propose a new architecture, MEANet, with a main block, an extension block, and an adaptive block for the edge. The inference process can terminate at either the main block, the extension block, or the cloud. The MEANet is trained to categorize inputs into easy/hard/complex classes. The main block identifies instances of easy/hard classes and classifies easy classes with high confidence. Only data with high probabilities of belonging to hard classes would be sent to the extension block for prediction. Further, only if the neural network at the edge shows low confidence in the prediction, the instance is considered complex and sent to the cloud for further processing. The training technique lends to the majority of inference on edge devices while going to the cloud only for a small set of complex jobs, as determined by the edge. The performance of the proposed system is evaluated via extensive experiments using modified models of ResNets and MobileNetV2 on CIFAR-100 and ImageNet datasets. The results show that the proposed distributed model has improved accuracy and energy consumption, indicating its capacity to adapt.

arXiv comment41st IEEE International Conference on Distributed Computing Systems, 2021

References in corpus (14)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
• Continual Learning Through Synaptic Intelligence
• PACT: Parameterized Clipping Activation for Quantized Neural Networks
• Pruning Filters for Efficient ConvNets
• Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes
• SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
• Progress & Compress: A scalable framework for continual learning
• Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing
• A Low Effort Approach to Structured CNN Design Using PCA
• Deciding How to Decide: Dynamic Routing in Artificial Neural Networks
• Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge Intelligence
• Conditionally Deep Hybrid Neural Networks Across Edge and Cloud