Research

Paper

AI LLM February 19, 2026

Federated Latent Space Alignment for Multi-user Semantic Communications

Authors

Giuseppe Di Poce, Mario Edoardo Pandolfo, Emilio Calvanese Strinati, Paolo Di Lorenzo

Abstract

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.

Metadata

arXiv ID: 2602.17271
Provider: ARXIV
Primary Category: cs.IT
Published: 2026-02-19
Fetched: 2026-02-21 18:51

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17271v1</id>\n    <title>Federated Latent Space Alignment for Multi-user Semantic Communications</title>\n    <updated>2026-02-19T11:18:58Z</updated>\n    <link href='https://arxiv.org/abs/2602.17271v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17271v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.IT'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-19T11:18:58Z</published>\n    <arxiv:primary_category term='cs.IT'/>\n    <arxiv:journal_ref>In 2025 IEEE 26th International Workshop on Signal Processing and Artificial Intelligence for Wireless Communications (SPAWC) (pp. 1-5). IEEE</arxiv:journal_ref>\n    <author>\n      <name>Giuseppe Di Poce</name>\n    </author>\n    <author>\n      <name>Mario Edoardo Pandolfo</name>\n    </author>\n    <author>\n      <name>Emilio Calvanese Strinati</name>\n    </author>\n    <author>\n      <name>Paolo Di Lorenzo</name>\n    </author>\n  </entry>"
}