# Semantic Feature Division Multiple Access for Multi-user Digital Interference Networks

arXiv: https://arxiv.org/abs/2407.08424 · HTML: https://mlsanity.com/paper/2407.08424/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2024.

## Built on by (most cited first, 3 of 3)

- [On-Air Deep Learning Integrated Semantic Inference Models for Enhanced Earth Observation Satellite Networks](https://mlsanity.com/paper/2409.15246/) (2024)
- [Prompt-Assisted Semantic Interference Cancellation on Moderate Interference Channels](https://mlsanity.com/paper/2408.04283/) (2024)
- [Way to Build Native AI-driven 6G Air Interface: Principles, Roadmap, and Outlook](https://mlsanity.com/paper/2508.15277/) (2025)

## Abstract (arXiv)

With the ever-increasing user density and quality of service (QoS) demand,5G networks with limited spectrum resources are facing massive access challenges. To address these challenges, in this paper, we propose a novel discrete semantic feature division multiple access (SFDMA) paradigm for multi-user digital interference networks. Specifically, by utilizing deep learning technology, SFDMA extracts multi-user semantic information into discrete representations in distinguishable semantic subspaces, which enables multiple users to transmit simultaneously over the same time-frequency resources. Furthermore, based on a robust information bottleneck, we design a SFDMA based multi-user digital semantic interference network for inference tasks, which can achieve approximate orthogonal transmission. Moreover, we propose a SFDMA based multi-user digital semantic interference network for image reconstruction tasks, where the discrete outputs of the semantic encoders of the users are approximately orthogonal, which significantly reduces multi-user interference. Furthermore, we propose an Alpha-Beta-Gamma (ABG) formula for semantic communications, which is the first theoretical relationship between inference accuracy and transmission power. Then, we derive adaptive power control methods with closed-form expressions for inference tasks. Extensive simulations verify the effectiveness and superiority of the proposed SFDMA.