Dynamic Split Computing for Efficient Deep Edge Intelligence

05/23/2022
by   Arian Bakhtiarnia, et al.
9

Deploying deep neural networks (DNNs) on IoT and mobile devices is a challenging task due to their limited computational resources. Thus, demanding tasks are often entirely offloaded to edge servers which can accelerate inference, however, it also causes communication cost and evokes privacy concerns. In addition, this approach leaves the computational capacity of end devices unused. Split computing is a paradigm where a DNN is split into two sections; the first section is executed on the end device, and the output is transmitted to the edge server where the final section is executed. Here, we introduce dynamic split computing, where the optimal split location is dynamically selected based on the state of the communication channel. By using natural bottlenecks that already exist in modern DNN architectures, dynamic split computing avoids retraining and hyperparameter optimization, and does not have any negative impact on the final accuracy of DNNs. Through extensive experiments, we show that dynamic split computing achieves faster inference in edge computing environments where the data rate and server load vary over time.

READ FULL TEXT
research
01/15/2021

Dynamic DNN Decomposition for Lossless Synergistic Inference

Deep neural networks (DNNs) sustain high performance in today's data pro...
research
06/22/2023

Slimmable Encoders for Flexible Split DNNs in Bandwidth and Resource Constrained IoT Systems

The execution of large deep neural networks (DNN) at mobile edge devices...
research
09/17/2023

SplitEE: Early Exit in Deep Neural Networks with Split Computing

Deep Neural Networks (DNNs) have drawn attention because of their outsta...
research
08/24/2022

A Low-Complexity Approach to Rate-Distortion Optimized Variable Bit-Rate Compression for Split DNN Computing

Split computing has emerged as a recent paradigm for implementation of D...
research
07/27/2020

Split Computing for Complex Object Detectors: Challenges and Preliminary Results

Following the trends of mobile and edge computing for DNN models, an int...
research
03/22/2023

Split-Et-Impera: A Framework for the Design of Distributed Deep Learning Applications

Many recent pattern recognition applications rely on complex distributed...
research
10/10/2021

SplitPlace: Intelligent Placement of Split Neural Nets in Mobile Edge Environments

In recent years, deep learning models have become ubiquitous in industry...

Please sign up or login with your details

Forgot password? Click here to reset