Generative Artificial Intelligence Assisted Multi-modal Semantic Extraction for NOMA-based Image Transmissions

2026-03-22

AI Summary

This work addresses the trade-off between semantic recovery accuracy and transmission latency in non-orthogonal multiple access (NOMA)-based image transmission by proposing a generative artificial intelligence–assisted semantic communication framework. The framework jointly optimizes semantic feature selection, receive beamforming, and NOMA decoding order, and introduces an importance-aware, model-driven proximal policy optimization algorithm (IM-PPO) to preserve high-importance semantic features while enhancing policy learning efficiency. Experimental results demonstrate that the proposed method significantly outperforms existing benchmark schemes in both semantic recovery accuracy and transmission latency, effectively achieving a synergistic improvement in semantic communication performance and system efficiency.

Technology Category

• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV
• Machine Learning: Optimization

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

In this paper, we investigate a generative artificial intelligence (GAI)-assisted semantic communication framework for non-orthogonal multiple access (NOMA)-based image transmissions. Semantic users (SUs) extract cross-modal semantic features from the raw images, which are then used for image recovery by leveraging a GAI model. The GAI enhances the generalization and recovery of semantic image transmissions, while NOMA efficiently allocates transmission capacities to SUs based on their traffic demands. Thus, the semantic extraction and transmission control jointly affect both semantic recovery performance and transmission overhead. We maximize a weighted performance of transmission latency and semantic recovery accuracy by jointly optimizing the semantic feature selection at the semantic level, as well as the receive beamforming and NOMA decoding order at the transmission level. To reduce potential redundancy in semantic features and improve optimization efficiency, we develop an importance-aware and model-driven proximal policy optimization (IM-PPO) framework. Specifically, we quantify and retain high-importance semantic features to enhance the learning efficiency of PPO, while model-based optimization methods are used to adapt the transmission control variables. Numerical results validate that the joint adjustment of the semantic feature selection and the transmission control significantly improves the semantic recovery accuracy and the transmission latency performance. Moreover, the IM-PPO framework effectively leverages the model information to improve the learning efficiency compared to benchmark methods.

Problem

• semantic communication
• NOMA
• image transmission
• semantic extraction
• transmission latency

Innovation

• Generative AI
• Semantic Communication
• NOMA
• Feature Importance
• Model-driven Optimization