# Over-the-Air Edge Inference via End-to-End Metasurfaces-Integrated Artificial Neural Networks arXiv: https://arxiv.org/abs/2504.00233 ยท HTML: https://mlsanity.com/paper/2504.00233/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Builds on 36 of its 71 references that are in the map. - First posted on arXiv 31 Mar 2025. ## Builds on (most cited first, 30 of 36) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015) - [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015) - [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017) - [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015) - [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018) - [Deep Learning Enabled Semantic Communication Systems](https://mlsanity.com/paper/2006.10685/) (2020) - [All-Optical Machine Learning Using Diffractive Deep Neural Networks](https://mlsanity.com/paper/1804.08711/) (2018) - [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022) - [Deep Learning-Based Communication Over the Air](https://mlsanity.com/paper/1707.03384/) (2017) - [Wireless Image Retrieval at the Edge](https://mlsanity.com/paper/2007.10915/) (2020) - [Noisy Activation Functions](https://mlsanity.com/paper/1603.00391/) (2016) - [Goal-Oriented and Semantic Communication in 6G AI-Native Networks: The 6G-GOALS Approach](https://mlsanity.com/paper/2402.07573/) (2024) - [Joint Source-Channel Coding: Fundamentals and Recent Progress in Practical Designs](https://mlsanity.com/paper/2409.17557/) (2024) - [Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions](https://mlsanity.com/paper/2307.00974/) (2023) - [Metasurface-Enabled On-Chip Multiplexed Diffractive Neural Networks in the Visible](https://mlsanity.com/paper/2107.07873/) (2021) - [FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion](https://mlsanity.com/paper/2406.03280/) (2024) - [Pervasive Machine Learning for Smart Radio Environments Enabled by Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2205.03793/) (2022) - [Over-the-Air Computation for 6G: Foundations, Technologies, and Applications](https://mlsanity.com/paper/2210.10524/) (2022) - [Stacked Intelligent Metasurfaces for Efficient Holographic MIMO Communications in 6G](https://mlsanity.com/paper/2305.08079/) (2023) - [Goal-oriented Communications for the IoT: System Design and Adaptive Resource Optimization](https://mlsanity.com/paper/2310.13948/) (2023) - [Phase Configuration Learning in Wireless Networks with Multiple Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/2010.04376/) (2020) - [Goal-Oriented Communication for Edge Learning based on the Information Bottleneck](https://mlsanity.com/paper/2202.12639/) (2022) - [Hybrid Reconfigurable Intelligent Metasurfaces: Enabling Simultaneous Tunable Reflections and Sensing for 6G Wireless Communications](https://mlsanity.com/paper/2104.04690/) (2021) - [Enabling Edge Artificial Intelligence via Goal-oriented Deep Neural Network Splitting](https://mlsanity.com/paper/2312.03555/) (2023) - [Reconfigurable Intelligent Surfaces for 6G: Emerging Hardware Architectures, Applications, and Open Challenges](https://mlsanity.com/paper/2312.16874/) (2023) - [Towards Distributed and Intelligent Integrated Sensing and Communications for 6G Networks](https://mlsanity.com/paper/2402.11630/) (2024) - [Multi-User MISO with Stacked Intelligent Metasurfaces: A DRL-Based Sum-Rate Optimization Approach](https://mlsanity.com/paper/2408.04837/) (2024) - [Metasurfaces-Enabled Wave Computing for Future Wireless Systems: Opportunities and Challenges](https://mlsanity.com/paper/2501.05173/) (2025) - [Reconfigurable Intelligent Computational Surfaces: When Wave Propagation Control Meets Computing](https://mlsanity.com/paper/2208.04509/) (2022) ## Built on by (most cited first, 7 of 7) - [Integrating Stacked Intelligent Metasurfaces and Power Control for Dynamic Edge Inference via Over-The-Air Neural Networks](https://mlsanity.com/paper/2509.18906/) (2025) - [Over-The-Air Extreme Learning Machines with XL Reception via Nonlinear Cascaded Metasurfaces](https://mlsanity.com/paper/2601.17749/) (2026) - [RIS-Enabled Smart Wireless Environments: Fundamentals and Distributed Optimization](https://mlsanity.com/paper/2512.18788/) (2025) - [Relay-Assisted Activation-Integrated SIM for Wireless Physical Neural Networks](https://mlsanity.com/paper/2604.04212/) (2026) - [Multi-layer MIMO Relay as Deep Physical Neural Networks: Power Amplifiers as Activation Functions](https://mlsanity.com/paper/2607.18354/) (2026) - [Over-The-Air Extreme Learning Machines with Nonlinear Stacked Intelligent Metasurfaces](https://mlsanity.com/paper/2608.27137/) (2026) - [RAOA: Alternating-Operator Neural Computation with Programmable Radio Propagation](https://mlsanity.com/paper/2610.02683/) (2026) ## Abstract (arXiv) In the Edge Inference (EI) paradigm, where a Deep Neural Network (DNN) is split across the transceivers to wirelessly communicate goal-defined features in solving a computational task, the wireless medium has been commonly treated as a source of noise. In this paper, motivated by the emerging technologies of Reconfigurable Intelligent Surfaces (RISs) and Stacked Intelligent Metasurfaces (SIM) that offer programmable propagation of wireless signals, either through controllable reflections or diffractions, we optimize the RIS/SIM-enabled smart wireless environment as a means of over-the-air computing, resembling the operations of DNN layers. We propose a framework of Metasurfaces-Integrated Neural Networks (MINNs) for EI, presenting its modeling, training through a backpropagation variation for fading channels, and deployment aspects. The overall end-to-end DNN architecture is general enough to admit RIS and SIM devices, through controllable reconfiguration before each transmission or fixed configurations after training, while both channel-aware and channel-agnostic transceivers are considered. Our numerical evaluation showcases metasurfaces to be instrumental in performing image classification under link budgets that impede conventional communications or metasurface-free systems. It is demonstrated that our MINN framework can significantly simplify EI requirements, achieving near-optimal performance with 50~dB lower testing signal-to-noise ratio compared to training, even without transceiver channel knowledge.