Over-the-Air Goal-Oriented Communications
2025/12/23 by Stylianopoulos, Kyriakos, Di Lorenzo, Paolo, Alexandropoulos, George C.
#Emerging Technologies (cs.ET) #FOS: Computer and information sciences #FOS: Electrical engineering #Information Theory (cs.IT) #Machine Learning (cs.LG) #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · doi:10.48550/arxiv.2512.20533
Abstract
Goal-oriented communications offer an attractive alternative to the Shannon-based communication paradigm, where the data is never reconstructed at the Receiver (RX) side. Rather, focusing on the case of edge inference, the Transmitter (TX) and the RX cooperate to exchange features of the input data that will be used to predict an unseen attribute of them, leveraging information from collected data sets. This chapter demonstrates that the wireless channel can be used to perform computations over the data, when equipped with programmable metasurfaces. The end-to-end system of the TX, RX, and MS-based channel is treated as a single deep neural network which is trained through backpropagation to perform inference on unseen data. Using Stacked Intelligent Metasurfaces (SIM), it is shown that this Metasurfaces-Integrated Neural Network (MINN) can achieve performance comparable to fully digital neural networks under various system parameters and data sets. By offloading computations onto the channel itself, important benefits may be achieved in terms of energy consumption, arising from reduced computations at the transceivers and smaller transmission power required for successful inference.
Citations
- RIS-Aided Localization and Sensing
- AirCNN via Reconfigurable Intelligent Surfaces: Architecture Design and Implementation
- Integrating Stacked Intelligent Metasurfaces and Power Control for Dynamic Edge Inference via Over-The-Air Neural Networks
- Parametrized Stacked Intelligent Metasurfaces for Bistatic Integrated Sensing and Communications
- Universal Approximation with XL MIMO Systems: OTA Classification via Trainable Analog Combining
- Doubly-Dispersive MIMO Channels with Stacked Intelligent Metasurfaces: Modeling, Parametrization, and Receiver Design
- Metasurfaces-Enabled Wave Computing for Future Wireless Systems: Opportunities and Challenges
- Optimizing RIS Impairments through Semantic Communication
- Joint Source-Channel Coding: Fundamentals and Recent Progress in Practical Designs
- Asymptotically Optimal Closed-Form Phase Configuration of 1-bit RISs via Sign Alignment
- Near-Field Beam Tracking with Extremely Large Dynamic Metasurface Antennas
- Enabling Edge Artificial Intelligence via Goal-oriented Deep Neural Network Splitting
- Stacked Intelligent Metasurfaces for Efficient Holographic MIMO Communications in 6G
- RIS-Enabled Smart Wireless Environments: Deployment Scenarios, Network Architecture, Bandwidth and Area of Influence
- Integrated Sensing and Communications with Reconfigurable Intelligent Surfaces
- Reconfigurable Intelligent Surfaces and Capacity Optimization: A Large System Analysis
- Reconfigurable Intelligent Computational Surfaces: When Wave Propagation Control Meets Computing
- Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications
- Online RIS Configuration Learning for Arbitrary Large Numbers of 1-Bit Phase Resolution Elements
- Reconfigurable Intelligent Surfaces for Wireless Communications: Overview of Hardware Designs, Channel Models, and Estimation Techniques
- Goal-Oriented Communication for Edge Learning based on the Information Bottleneck
- Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
- Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications
- Low-to-Zero-Overhead IRS Reconfiguration: Decoupling Illumination and Channel Estimation
- Hybrid Reconfigurable Intelligent Metasurfaces: Enabling Simultaneous Tunable Reflections and Sensing for 6G Wireless Communications
- Phase Configuration Learning in Wireless Networks with Multiple\n Reconfigurable Intelligent Surfaces
- Wireless Image Retrieval at the Edge
- Indoor Signal Focusing with Deep Learning Designed Reconfigurable Intelligent Surfaces
- A Survey on Deep Transfer Learning
- Noisy Activation Functions
- Variational Dropout and the Local Reparameterization Trick
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- Adam: A Method for Stochastic Optimization
- A Stochastic Approximation Method
- Towards Goal-Oriented Semantic Communications: New Metrics, Framework, and Open Challenges
Related