Multi-view Semantic-aware Resource Allocation for Edge AI

Jiawei Luo; Hussein Saleh; Mohamad Assaad

cs.ITOct 25, 2026

Multi-view Semantic-aware Resource Allocation for Edge AI

Authors: Jiawei Luo, Hussein Saleh, Mohamad Assaad

Organizations: Laboratoire des Signaux et Systèmes (L2S), CentraleSupélec, Université Paris-Saclay Gif-sur-Yvette, France

Abstract

Semantic communication is emerging as a pivotal paradigm to overcome wireless resource scarcity in 6G networks. This paper proposes a novel end-to-end framework for semantics-aware resource allocation in multi-user Edge AI. We extend the Opportunistic Information Bottleneck (OIB) to a multi-view setting, termed the Multi-view Gaussian Information Bottleneck (MGIB), by fusing complementary source views without variational approximation or network retraining. A resource allocation framework is then formulated for joint compression-level selection, transmission mode selection (i.e., the number of active sources per group), and PRB assignment. The problem is formulated as a Mixed-Integer Linear Program (MILP), solved efficiently via a proposed Lagrangian Relaxation (LR) algorithm, and benchmarked against the NP-hard optimal solution. Simulations demonstrate that the proposed LR scheme achieves near-optimal utility, and doubles PRB efficiency versus average allocation.

Figures & tables

Panel of Figure 1 — Fig. 1: End-to-end MGIB-based semantic communication system for multi-view Edge AI inference.

Component	Layer Type	Shape (In $\rightarrow$ Out)
M ref Classifier	Linear + ReLU	256 $\rightarrow$ 128
	Linear + ReLU	128 $\rightarrow$ 64
	Linear + ReLU	64 $\rightarrow$ 16
	Linear	16 $\rightarrow$ 10
Attention Module	Linear + ReLU	512 (256+256) $\rightarrow$ 128
	Linear + Sigmoid	128 $\rightarrow$ 256

TABLE I: Network Architectures

Fig. 2: MGIB vs. single-view baselines on MNIST Rotation+Noisy.

Method	Accuracy
Linear CCA	0.579
DCCA [ 8 ]	0.747
DCCAE	0.622
Deep Multi-view IB (SIAM 2019) [ 9 ]	0.823
MEIB (ICASSP 2022) [ 10 ]	0.828
MGIB (ours)	0.950

TABLE II: SOTA Comparison on MNIST Rotation+Noisy Dataset

Fig. 3: Utility of the LR vs. MILP optimal and Average+Random baseline.

Parameter	Value
Number of Groups, $K$	15
Sources per Group $C$	4
PRBs $R$	$\{5,8,9,10,15,20,25,30,35,40,50,60,70\}$
Cell radius $R_{\text{cell}}$	1 km
Transmit power $p$ per PRB	250 mW
Noise power $\sigma^{2}$	$-104$ dBm

TABLE III: Simulation Parameters

Wireless Resource Allocation

Wireless resource allocation assigns spectrum, power, beams, and computing capacity to meet throughput, latency, fairness, and energy goals.

See all 175 papers

Optimization-as-a-Service via Multi-Agent Large Language Model for Radio Access Networks
May 15, 2026Chaoqun You, Yueyue Dai, Xingqiu He +3Multi-Agent System Optimization Large Language Model-Guided Optimization
Fudan University · Huazhong University of Science and Technology · University of Surrey +1
GAN-Enhanced Deep Reinforcement Learning for Semantic-Aware Resource Allocation in 6G Network Slicing
Mar 27, 2026Daniel Benniah JohnNetwork Slicing Wireless Resource Allocation
University of California, Berkeley, CA, USA
Minimizing Quantized Semantic Age of Information (QSAoI) in Foundation Model-Based Semantic Communications
Jun 30, 2026Huanyu Zhang, Yulin Hu, Xiaopeng Yuan +2Mixed-Precision Quantization Semantic Communication
INDA Chair, RWTH Aachen University, Germany · School of Electronic Information, Wuhan University, China · Department of Digital Communication Systems, Ruhr University Bochum, Germany

May 15, 2026J/K move · Enter open · S save

Optimization-as-a-Service via Multi-Agent Large Language Model for Radio Access Networks

Chaoqun You, Yueyue Dai, Xingqiu He, Yue Gao+2

Fudan University · Huazhong University of Science and Technology · University of Surrey+1

Multi-Agent System Optimization Large Language Model-Guided Optimization Wireless Communications Wireless Resource Allocation Multi-Agent LLMs

Open paper AskPDF arXiv

The physical resource block (PRB) allocation in Radio Access Networks (RANs) traditionally relies on case-by-case manual problem construction or, more recently, learning-based artificial intelligence (AI) methods. However, the sixth-generation (6G) RAN environments confront unprecedented service diversity and exponential dynamics, featuring volatile fluctuations in active base stations (BSs), user scale, and stringent Quality-of-Service (QoS) requirements. Faced with such conditions, both manual models and standard AI algorithms remain fundamentally rigid, lacking the flexibility to adapt and self-evolve. To provide a one-size-fits-all solution, we propose treating the PRB allocation problem as an Optimization-as-a-Service (OaaS) provided by a large language model multi-agent (LLM-MA) system. This fundamentally reshapes RAN resource allocation by utilizing agents to dynamically construct optimization problems and automatically determine objectives tailored to real-time scenarios. Our closed-loop architecture, integrating scene understanding, objective generation, solver, and reflection agents, enables context-aware, self-correcting formulation. To eliminate the computational latency of iterative reflection, we introduce a one-shot reflection distillation mechanism, training a lightweight student model to directly predict refined objective parameters. We theoretically bound the performance gap of this one-shot policy. Experimental results demonstrate our framework achieves near-optimal resource allocation with ultra-low inference latency.

Abstract

Wireless Resource Allocation

Explore similar work

Optimization-as-a-Service via Multi-Agent Large Language Model for Radio Access Networks

GAN-Enhanced Deep Reinforcement Learning for Semantic-Aware Resource Allocation in 6G Network Slicing

Minimizing Quantized Semantic Age of Information (QSAoI) in Foundation Model-Based Semantic Communications