Federated Latent Space Alignment for Multi-user Semantic Communications

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

cs.ITFeb 19, 2026

Federated Latent Space Alignment for Multi-user Semantic Communications

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

Organizations: CEA Leti, University Grenoble Alpes, 38000, Grenoble, France. · DIAG Department, Sapienza University of Rome, via Ariosto 25, Rome, Italy. · Consorzio Nazionale Interuniversitario per le Telecomunicazioni (CNIT), Parma, Italy. · DIET Department, Sapienza University of Rome, Via Eudossiana 18, Rome, Italy.

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.

Figures & tables

Fig. 1: Overview of the proposed system model.

Group	Models
AP	vit_tiny_patch16
Users	efficientvit_m5, levit_128, rexnet_100,
	vit_small_patch{16,32}, vit_base_patch{16,32},
	mobilenet_v3_small_{075,100}, mobilenet_v3_large_100
Heterogeneous	vit_{small,base}_patch16_224,
	mobilenetv3_small_075, efficientvit_m5

TABLE I: Models Configuration

Fig. 2: Accuracy vs.

\zeta

with SNR=20 dB.

Fig. 3: Alignment struggle as Network MSE and Accuracy vs.

\zeta

for a 4

\times

4 MIMO channel with SNR=20 dB.

Semantic Communication

Semantic communication sends meaning- or task-relevant information so receivers can act without reconstructing every transmitted bit or signal.

See all 103 papers

Proxifield: Decentralized Multi-Agent Communication through Semantic Proximity
Sep 16, 2026Pradyumna Tambwekar, Yenchia Feng, Deep Patel +1Multi-Agent LLM Systems Multi-Agent Coordination
Distyl AI
When Semantic Communication Meets Queueing: Cross-Layer Latency and Task Fidelity Optimization
May 6, 2026Yalin E. Sagduyu, Tugba ErpekSemantic Communication Age of Information
Nexcepta, Gaithersburg, MD, USA
SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking
May 7, 2026Yong Xiao, Haoran Zhou, Yujie Zhou +1Agent Communication Protocols Semantic Communication
School of Elect. Inform. & Commun., Huazhong Univ. of Science & Technology, China · Peng Cheng Laboratory, Shenzhen, China · Pazhou Laboratory (Huangpu), Guangzhou, China +1

Sep 16, 2026J/K move · Enter open · S save

Proxifield: Decentralized Multi-Agent Communication through Semantic Proximity

Pradyumna Tambwekar, Yenchia Feng, Deep Patel, Karime Maamari

Distyl AI

Multi-Agent LLM Systems Multi-Agent Coordination Agent Communication Protocols Multi-Agent Systems Multi-Agent Communication Multi-Agent Communication Topology

Open paper AskPDF arXiv

As LLM capabilities have expanded, multi-agent communication has emerged as an increasingly active area of research. Prevailing protocols often adopt rigid structures that introduce coordination bottlenecks and can degrade as the number of agents increases. We introduce Proxifield, a round-adaptive multi-agent protocol with decentralized agent decision-making that constructs sparse communication graphs from the evolving semantic proximity of agents. Without model training or a centralized planner, Proxifield connects agents using four routing signals derived at inference time: direct address, information needs, plan alignment, and information complementarity. We compare Proxifield with two representative coordination baselines, a centralized Star protocol and a decentralized Shared Context protocol, across two domains: Drone Search and Rescue and the collective-reasoning benchmark HiddenBench. We first ablate base-model capability and find that, in both domains, the performance of Proxifield improves with model size (35B -> 397B parameter model) and Proxifield outperforms all baselines at the largest scale. As team size increases, Proxifield's task-reward advantage over Star widens from 5.4% at (N=5) to 53.0% at (N=25) and 59.5% at (N=50), while Shared Context consistently underperforms both protocols. Proxifield is also substantially more robust to permanent agent failure, retaining 73.6% of its no-failure task reward under the most severe condition, compared with 58.3% for Shared Context and 38.8% for Star. These results demonstrate that decentralized, semantically adaptive routing can improve the scalability and fault tolerance of multi-agent systems.

Abstract

Semantic Communication

Explore similar work

Proxifield: Decentralized Multi-Agent Communication through Semantic Proximity

When Semantic Communication Meets Queueing: Cross-Layer Latency and Task Fidelity Optimization

SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking