SemDA: Communication-Efficient Data Aggregation Through Distributed Semantic Transmission
Authors:
- 14 April 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9196-9200
Abstract
This paper introduces SemDA, a communication-efficient data aggregation method that uses distributed semantic communication for improved transmission and analysis. SemDA utilizes an end-to-end trainable network structure that reduces data transmission volume and deepens semantic feature aggregation. Key advances include an attention-based aggregation method for holistic semantic feature integration and a dual-attention decoding network that emphasizes viewpoint and content dimensions. Performance evaluations on CIFAR-10 and ImageNet datasets show that SemDA offers significant improvements in accuracy and system overhead compared to traditional and distributed semantic communication methods. Notable contributions include the proposal of a novel decoding structure, the introduction of a dual-attention decoding mechanism, and extensive evaluations against benchmark methods.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 14 references indexed in Scilit:
- Communication-Efficient Framework for Distributed Image Semantic Wireless TransmissionIEEE Internet of Things Journal, 2023
- WiserVR: Semantic Communication Enabled Wireless Virtual Reality DeliveryIEEE Wireless Communications, 2023
- Collaborative Semantic Communication for Edge InferenceIEEE Wireless Communications Letters, 2023
- Cooperative multi-camera vehicle tracking and traffic surveillance with edge artificial intelligence and representation learningTransportation Research Part C: Emerging Technologies, 2023
- Toward Semantic Communications: Deep Learning-Based Image Semantic CodingIEEE Journal on Selected Areas in Communications, 2022
- A Robust and Optional Privacy Data Aggregation Scheme for Fog-Enhanced IoT NetworkIEEE Systems Journal, 2022
- Semantic Communications: Overview, Open Issues, and Future Research DirectionsIEEE Wireless Communications, 2022
- Deep Joint Source-Channel Coding for Wireless Image TransmissionIEEE Transactions on Cognitive Communications and Networking, 2019
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009