Joint Device-Edge Inference over Wireless Links with Pruning

Abstract

We propose a joint feature compression and transmission scheme for efficient inference at the wireless network edge. Our goal is to enable efficient and reliable inference at the edge server assuming limited computational resources at the edge device. Previous work focused mainly on feature compression, ignoring the computational cost of channel coding. We incorporate the recently proposed deep joint source-channel coding (DeepJSCC) scheme, and combine it with novel filter pruning strategies aimed at reducing the redundant complexity from neural networks. We evaluate our approach on a classification task, and show improved results in both end-to-end reliability and workload reduction at the edge device. This is the first work that combines DeepJSCC with network pruning, and applies it to image classification over the wireless edge.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Deep Joint Source-Channel Coding for Wireless Image Transmission
• End-to-end Optimized Image Compression
• Pruning Convolutional Neural Networks for Resource Efficient Inference
• Density Modeling of Images using a Generalized Normalization Transformation
• JALAD: Joint Accuracy- and Latency-Aware Deep Structure Decoupling for Edge-Cloud Execution
• Deep Joint Source-Channel Coding for Wireless Image Retrieval

Cited by in corpus (18)

• Edge Learning for B5G Networks with Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing
• Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
• BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing
• Distributed Learning in Wireless Networks: Recent Progress and Future Challenges
• Constellation Design for Deep Joint Source-Channel Coding
• I-SPLIT: Deep Network Interpretability for Split Computing
• LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks
• A Lite Distributed Semantic Communication System for Internet of Things
• Private Collaborative Edge Inference via Over-the-Air Computation
• Semantic Communication Systems for Speech Transmission
• Slimmable Encoders for Flexible Split DNNs in Bandwidth and Resource Constrained IoT Systems
• Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation
• Semantic Communications for Speech Signals
• Deep Joint Source-Channel Coding for Multi-Task Network
• Remote Anomaly Detection in Industry 4.0 Using Resource-Constrained Devices
• Semantic Communications for Speech Recognition
• Communication-Computation Efficient Device-Edge Co-Inference via AutoML
• Over-the-Air Multi-Sensor Inference with Neural Networks Using Memristor-Based Analog Computing