Computational Efficient Width-Wise Early Exiting in Wireless Communication Systems

TL;DR

This paper introduces a width-wise early exiting strategy for CNNs in wireless communication, significantly reducing computational load while maintaining performance, especially in high-SNR scenarios.

Contribution

It proposes a novel width-wise exiting method for CNNs that adjusts input size to lower computational demands without sacrificing accuracy.

Findings

26% average reduction in computational load

60% reduction in high-SNR scenarios

Effective in Modulation Classification tasks

Abstract

Deep learning (DL) techniques are increasingly pervasive across various domains, including wireless communication, where they extract insights from raw radio signals. However, the computational demands of DL pose significant challenges, particularly in distributed wireless networks like Cell-free networks, where deploying DL models on edge devices becomes hard due to heightened computational loads. These computational loads escalate with larger input sizes, often correlating with improved model performance. To mitigate this challenge, Early Exiting (EE) techniques have been introduced in DL, primarily targeting the depth of the model. This approach enables models to exit during inference based on specified criteria, leveraging entropy measures at intermediate exits. Doing so makes less complex samples exit early, reducing the average computational load and inference time. In our contribution, we propose a novel width-wise exiting strategy for Convolutional Neural Network (CNN)-based architectures. By selectively adjusting the input size, we aim to regulate computational demands effectively. Our approach aims to decrease the average computational load during inference while maintaining performance levels comparable to conventional models. We specifically investigate Modulation Classification, a well-established application of DL in wireless communication. Our experimental results show substantial reductions in computational load, with an average decrease of 26%, and particularly notable reductions of 60% in high-SNR scenarios. Through this work, we present a practical solution for reducing computational demands in deep learning applications, particularly within the domain of wireless communication.