Over-the-Air Semantic Alignment via Dual Stacked Intelligent Metasurfaces
Organizations: the DIAG and DIET Departments, Sapienza University of Rome, Italy · the National Inter-University Consortium for Telecommunications (CNIT), Parma, Italy · the Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Greece · the DIET Department, Sapienza University of Rome, 00184 Rome, Italy
Abstract
Semantic communications enable task-oriented information exchange, but suffer from latent-space mismatch when transmitter and receiver employ heterogeneous machine learning models. Existing semantic alignment methods rely on digital processing, introducing computational and latency overhead. This paper proposes a dual stacked intelligent metasurfaces (dual-SIM) architecture that performs semantic alignment entirely in the wave domain. By jointly exploiting programmable metasurfaces at both ends of a link and the wireless channel, the proposed architecture realizes an end-to-end linear transformation between heterogeneous latent spaces. We show phase-only multilayer SIM can approximate both supervised linear aligners and zero-shot Parseval-frame equalizers. We investigate single-SIM, disjoint asymmetric and symmetric dual-SIM, and jointly optimized dual-SIM configurations, considering channel equalization and constructive channel exploitation. For joint design, we develop an alternating projected gradient algorithm with convergence guarantees to first-order stationary points. We further introduce a deep-unrolled network that unrolls gradient-based iterations to reduce computational cost of SIM reconfiguration under channel variations. Numerical results with heterogeneous vision transformer encoders show accurate semantic alignment from moderate to high signal-to-noise ratios. The joint and symmetric disjoint dual-SIM designs achieve the highest accuracy over compact channels, the joint design leads at shallow stack depths, and the advantage over single-SIM designs diminishes at equal depth.
Figures & tables
| Configuration | TX SIM | RX SIM | Requirements | ||||||
| Digital Equalizer | Perfect CSI | Admissible | |||||||
| Mono TX, equalized | – | – | – | , | |||||
| Mono TX, constructive | – | – | – | – | |||||
| Mono RX, constructive | – | – | – | – | |||||
| Disj.-asym. TX, equalized | – | , | |||||||
| Disj.-asym. TX, constructive | – | , | |||||||
Appendix figures & tables5 assets
Supplementary material from the paper’s appendix.
Appendix
| Linear probe | MLP | ||||||
| Baseline | Channel | Unrolled | Peak (iteration) | At | Unrolled | Peak (iteration) | At |
| With semantic warm start | |||||||
| 77.9 | 80.3 (8605) | 79.1 | 77.4 | 80.0 (9431) | 78.3 | ||
| 75.6 | 60.4 (107) | 46.8 | 73.4 | 56.6 (212) | 45.0 | ||
| 71.6 | 32.5 (81) | 20.1 | 68.3 | 26.7 (42) | 15.7 | ||
| Rayleigh | 71.6 | 12.1 (9) | 11.4 | 67.8 | 10.1 (18) | 10.0 | |
Semantic Communication
Semantic communication sends meaning- or task-relevant information so receivers can act without reconstructing every transmitted bit or signal.
See all 117 papers