Multi-view Semantic-aware Resource Allocation for Edge AI

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.

DiffLyap-MEC: Diffusion-Guided Lyapunov Optimization for Joint Offloading, Semantic Compression, and Resource Allocation in ISAC-Enabled 6G Edge Computing
Abrar S. Alhazmi, Mohammed M. Alenazi
Mathematics14 Oct 2026Peer-reviewedCC BY 4.0General mathematicsCrossref
Resource-Constrained Semantic-Aware Remote Estimation with Overlapping Sensor Coverage
Bowen Sun, Nikolaos Pappas
arXiv7 Sep 2026PreprintarXiv licenceFull textGeneral mathematicsarXiv
Performance Analysis and Sensing-Aware Resource Allocation for Full-Duplex Massive MIMO ISCC Networks
Vo Phi Son, Van-Dinh Nguyen, Nhan Thanh Nguyen +2
arXiv6 Oct 2026PreprintCC BY 4.0Full textGeneral mathematicsarXiv
TAVRUM: Feasibility-First Contract Matching for Fragmentation-Aware Resource Allocation in IoT–Fog Networks
Deafallah Alsadie
Mathematics30 Sep 2026Peer-reviewedCC BY 4.0General mathematicsCrossref
Latency-Aware Uplink NOMA-MEC with PASS: A Feasibility-First Resource Allocation Framework
Sepehr Abolhasani, Saba Asaad, S. Mohammad Razavizadeh +1
arXiv13 Oct 2026PreprintarXiv licenceFull textGeneral mathematicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{luo2026multiview,
  title = {{Multi-view Semantic-aware Resource Allocation for Edge AI}},
  author = {Jiawei Luo and Hussein Saleh and Mohamad Assaad},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.34532},
  eprint = {2610.34532},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.34532},
}

RIS

TY  - UNPB
TI  - Multi-view Semantic-aware Resource Allocation for Edge AI
AU  - Jiawei Luo
AU  - Hussein Saleh
AU  - Mohamad Assaad
PY  - 2026
DA  - 2026/10/25
PB  - arXiv
DO  - 10.48550/arxiv.2610.34532
UR  - https://arxiv.org/abs/2610.34532
AB  - 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.
ER  -

Abstract

Related

Cite