Federated Latent Space Alignment for Multi-user Semantic Communications
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910026907516928 |
|---|---|
| author | Di Poce, Giuseppe Pandolfo, Mario Edoardo Strinati, Emilio Calvanese Di Lorenzo, Paolo |
| author_facet | Di Poce, Giuseppe Pandolfo, Mario Edoardo Strinati, Emilio Calvanese Di Lorenzo, Paolo |
| contents | Semantic communication aims to convey meaning for effective task execution, but differing latent representations in AI-native devices can cause semantic mismatches that hinder mutual understanding. This paper introduces a novel approach to mitigating latent space misalignment in multi-agent AI- native semantic communications. In a downlink scenario, we consider an access point (AP) communicating with multiple users to accomplish a specific AI-driven task. Our method implements a protocol that shares a semantic pre-equalizer at the AP and local semantic equalizers at user devices, fostering mutual understanding and task-oriented communication while considering power and complexity constraints. To achieve this, we employ a federated optimization for the decentralized training of the semantic equalizers at the AP and user sides. Numerical results validate the proposed approach in goal-oriented semantic communication, revealing key trade-offs among accuracy, com- munication overhead, complexity, and the semantic proximity of AI-native communication devices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17271 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Federated Latent Space Alignment for Multi-user Semantic Communications Di Poce, Giuseppe Pandolfo, Mario Edoardo Strinati, Emilio Calvanese Di Lorenzo, Paolo Information Theory Artificial Intelligence Semantic communication aims to convey meaning for effective task execution, but differing latent representations in AI-native devices can cause semantic mismatches that hinder mutual understanding. This paper introduces a novel approach to mitigating latent space misalignment in multi-agent AI- native semantic communications. In a downlink scenario, we consider an access point (AP) communicating with multiple users to accomplish a specific AI-driven task. Our method implements a protocol that shares a semantic pre-equalizer at the AP and local semantic equalizers at user devices, fostering mutual understanding and task-oriented communication while considering power and complexity constraints. To achieve this, we employ a federated optimization for the decentralized training of the semantic equalizers at the AP and user sides. Numerical results validate the proposed approach in goal-oriented semantic communication, revealing key trade-offs among accuracy, com- munication overhead, complexity, and the semantic proximity of AI-native communication devices. |
| title | Federated Latent Space Alignment for Multi-user Semantic Communications |
| topic | Information Theory Artificial Intelligence |
| url | https://arxiv.org/abs/2602.17271 |