Federated Latent Space Alignment for Multi-user Semantic Communications

2026-02-19

AI Summary

This work addresses semantic mismatch in task-oriented multi-user AI-native semantic communication, arising from heterogeneous semantic representations across devices. To mitigate this issue, the paper proposes a novel downlink architecture featuring a semantic pre-equalizer at the access point and local semantic equalizers at user ends, jointly trained via a federated optimization strategy. This approach pioneers the integration of federated learning into multi-user semantic communication systems, enabling implicit semantic space alignment without sharing raw data. The proposed method effectively balances communication overhead, computational complexity, and task accuracy while preserving semantic consistency. Experimental results validate its efficacy in goal-oriented semantic communication and reveal key performance trade-offs among these competing objectives.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

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.

Problem

• semantic communication
• latent space misalignment
• multi-user
• AI-native devices
• semantic mismatch

Innovation

• Federated Learning
• Semantic Communication
• Latent Space Alignment
• Multi-user Systems
• Semantic Equalizer