STAR: Semantic-Criticality Tiered Allocation of Radio Resources via Zero-Shot Learning
Authors: Albert Shaju, Christo Kurisummoottil Thomas, Mingzhe Chen
Organizations: Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA · Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL, USA
In remote inference, edge devices transmit high-resolution images over wireless links to a receiver, where an artificial intelligence (AI) model answers task-specific questions about these images to enable reliable decisions. These answers are often determined by a small set of task-causal pixels, such as those of text, whose corruption changes the answer, so these pixels must be delivered with high fidelity. Conventional transmission protects every pixel equally, so it either consumes many resource elements (REs) or corrupts these regions at low signal-to-noise ratio (SNR). To overcome these limitations, in this paper, a zero-shot, domain-agnostic framework, termed semantic-criticality tiered allocation of resources (STAR), is proposed. In particular, a per-pixel semantic-criticality indicator (SCI) is derived from the attention of a frozen vision-language model, so new tasks and domains are handled by changing only the prompt, without retraining. The resulting task causality-aware resource allocation problem over protection tiers is solved exactly by a threshold rule on the SCI, realized by a coded tier for the task-causal pixels and an uncoded, downsampled base layer for the full image. Simulations over a 5G New Radio link demonstrate that STAR attains a semantic accuracy of at least 0.98 for Es/N0≥−4 dB and, at comparable semantic reliability, reduces the REs of robust coded transmission by 59.5% and 91.5% on factory- and vehicle-monitoring datasets, respectively, the latter without any change to the models. Although a deep joint source-channel coding baseline uses fewer REs at comparable semantic accuracy, it must be retrained with labeled data for every new task or domain.
Figures & tables
Fig. 1: Sample images from a factory-monitoring environment.
Fig. 2: Continuous SCI channel overlaid on a fire-event image for different sets of critical tasks.
Fig. 3: Received images of a fire-event image with 256 -QAM at Es/N0=2 dB.
Query
Sample answer
Which room is this?
Boiler Room
Equipment status?
Normal
Pressure reading?
3.8 bar
Temperature reading?
50∘ C
Power on Grid or Backup?
Grid
Is there a fire?
Yes / No
TABLE I: Queries of the factory-monitoring dataset and sample answers.
Fig. 4: Performance at D=4 on the factory-monitoring dataset.
Fig. 5: STAR at D=4 , the conventional scheme at D=1 , and the DeepJSCC on the factory-monitoring dataset.
Fig. 6: Factory-monitoring dataset. (a) REs per image of STAR, and the baselines. (b) Per-task S-Acc with 256 -QAM at Es/N0=2 dB, with only the room task critical for STAR.
Fig. 7: Vehicle-monitoring dataset, 256 -QAM at Es/N0=10 dB. (a) Original image. (b)–(d) Received image zoomed in to the number plate.
Fig. 8: S-Acc and S-PSNR of the plate task with 256-QAM. The upper bound is the S-Acc attained on the images at the transmitter.
Fig. 9: REs per image of the robust baseline and STAR.
Semantic communication (SC) systems transmit continuous latent representations of meaning, but computing the semantic encoder at resource-constrained edge devices incurs substantial energy and memory costs. To address this challenge, we propose an end-to-end SC framework that executes the semantic encoder in the client's RF receiver front end using analog RF computing. A base station (BS) broadcasts encoder weights as RF waveforms, while each edge device reuses its receiver's passive mixer to compute semantic latents at ultra-low energy. These latents are transmitted over the uplink for network-side task inference. We show that analog computing noise across encoder layers and channel noise affecting transmitted latents admit a unified mathematical model. We define a task-posterior semantic distortion metric and derive its second-order decomposition into per-client, per-stage semantic sensitivities. Using this decomposition, we obtain a closed-form semantic-aware water-filling allocation of the total client energy budget across clients, encoder layers, and uplinks, assigning tighter accuracy targets to semantically sensitive stages. This allocation induces a broadcast beamforming problem that accounts for client-specific, per-layer accuracy requirements. We further refine the allocation through stochastic optimization and jointly design it with multi-task noise-aware training of the shared semantic model. MNIST simulations show that, at matched total client energy, the proposed allocation reduces network semantic distortion by 9.2%-19.2% compared with uniform precision and 5.1%-13.1% compared with client-blind allocation. Noise-aware co-design yields a further 46% reduction.
Christo Kurisummoottil Thomas
Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA
Resource-constrained visual Internet of Things (IoT) systems, such as edge cameras, unmanned sensing platforms, industrial inspection nodes, and remote monitoring sensors, often need to transmit task-relevant visual evidence over low-rate wireless links to an edge/cloud service. Existing image communication methods usually compress or transmit complete global representations, leaving limited room to exploit receiver-side generative restoration. This paper proposes a semantic-aware generative image transmission framework for edge-assisted visual IoT. The image captured by an IoT visual sensor is encoded into a discrete token grid by a VQ encoder. At the IoT transmitter or nearby gateway, token recoverability, estimated from prediction entropy and local structure complexity, is fused with semantic importance obtained from instance segmentation and category-aware scoring. A spatial dispersal sampler then selects the tokens to be transmitted under a bitrate budget. The transmitter sends only the quantization indices of kept tokens and a binary mask map, while the edge/cloud receiver recovers masked tokens through MaskGIT with Halton sequence scheduling. Experiments on Kodak and VisDrone scenes under AWGN and Rayleigh channels show that the proposed method provides a flexible bitrate-quality tradeoff for narrowband visual IoT links. At 0.074 bpp, it uses 44.6% of the transmitted bits of the 0.167-bpp DeepJSCC/WITT reference while achieving 29.9 dB PSNR. A pseudo-GT downstream detection study on Kodak further shows that semantic-aware masking preserves task-relevant objects better than random masking at both 30% and 50% mask ratios.
Chenyang Zhang, Changwang Liu, Jinqi Zhu +4
School of Computer and Information Engineering, Tianjin Normal University, Tianjin, China · School of Information Science and Engineering, Linyi University, Linyi 276000, China
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.
Jiawei Luo, Hussein Saleh, Mohamad Assaad
Laboratoire des Signaux et Systèmes (L2S), CentraleSupélec, Université Paris-Saclay Gif-sur-Yvette, France