Learning to Interfere in Non-Orthogonal Multiple-Access Joint Source-Channel Coding

Selim F. Yilmaz; Can Karamanli; Deniz Gunduz

cs.NIMar 23, 2025

Learning to Interfere in Non-Orthogonal Multiple-Access Joint Source-Channel Coding

Authors: Selim F. Yilmaz, Can Karamanli, Deniz Gunduz

Organizations: Department of Electrical and Electronic Engineering, Imperial College London, United Kingdom. · School of Biomedical Engineering & Imaging Sciences, King’s College London, United Kingdom.

Abstract

We consider multiple transmitters aiming to communicate their source signals (e.g., images) over a multiple access channel (MAC). Conventional communication systems minimize interference by orthogonally allocating resources (time and/or bandwidth) among users, which limits their capacity. We introduce a machine learning (ML)-aided wireless image transmission method that merges compression and channel coding using a multi-view autoencoder, which allows the transmitters to use all the available channel resources simultaneously, resulting in a non-orthogonal multiple access (NOMA) scheme. The receiver must recover all the images from the received superposed signal, while also associating each image with its transmitter. Traditional ML models deal with individual samples, whereas our model allows signals from different users to interfere in order to leverage gains from NOMA under limited bandwidth and power constraints. We introduce a progressive fine-tuning algorithm that doubles the number of users at each iteration, maintaining initial performance with orthogonalized user-specific projections, which is then improved through fine-tuning steps. Remarkably, our method supports up to 64 users with potential for further scaling, with only a 2.4% increase in the number of trainable parameters compared to a single-user model, significantly enhancing recovered image quality and outperforming existing NOMA-based methods over a wide range of datasets, metrics, and channel conditions. Our approach paves the way for more efficient and robust multi-user communication systems, leveraging innovative ML components and strategies.

Figures & tables

Fig. 1: Extension of DeepJSCC to two users via TDMA.

Paper	Demonstrated Max # Users	Dataset(s)	Channel(s)	Coding	Modality	Uplink/Downlink
Ours	64	CIFAR,TinyImagenet, Cityscapes,Kodak	AWGN, Rayleigh	JSCC	Image	Uplink
DeepJSCC-NOMA [ 19 ]	2	CIFAR	AWGN	JSCC	Image	Uplink
DBC Aware JSCC [ 20 ]	2	CIFAR	AWGN	JSCC	Image	Downlink
NOMASC [ 21 ]	3	MNIST,CIFAR,Europarl	AWGN, Rayleigh	JSCC	Image, Text	Downlink
DeepSCM [ 22 ]	2	CIFAR	AWGN	JSCC	Image	Downlink
IS-SNOMA [ 23 ]	2	Cityscapes	Rician	JSCC	Image	Downlink

TABLE I: Comparison of Deep Learning Based Transmission Methods for NOMA

Fig. 2: Overall architecture of our DeepJSCC-PNOMA method. Due to the design of the user-specific projection matrices in DeepJSCC-PNOMA—which preserve the power of each encoded signal and enforce mutual orthogonality among signals—the system with $n$ users initially behaves as if it were time-sharing among $\frac{n}{2}$ users under fixed per-user average power $\bar{P}_{\mathrm{avg}}$ and per-user bandwidth ratio $\bar{\rho}$ . In this configuration, each user’s signal retains its original power and remains free from interference, enabling independent decoding. Consequently, the network can begin fine-tuning without any performance degradation from inter-user interference.

Fig. 3: Encoder architecture, user-specific projection layer and power normalization layer of the introduced method.

Fig. 4: User-specific projection layer and decoder architecture of the introduced method.

Panel of Figure 6 — Algorithm 1 Training and Fine-tuning of DeepJSCC-PNOMA

Fig. 5: Progressive fine-tuning methodology for scaling DeepJSCC-PNOMA from 1 to 16 users. The process iteratively doubles the number of users while maintaining training stability through orthogonal initialization. Each stage preserves signal power and ensures initial orthogonality between user groups, enabling convergence from interference-free configurations.

Panel of Figure 8 — Algorithm 2 Progressive fine-tuning for doubling the number of users in DeepJSCC-PNOMA

Fig. 6: Comparison with point-to-point DeepJSCC and separation-based methods.

$\bar{\rho}$	$\bar{P}_{\mathrm{avg}}$	$\sigma^{2}$	Method	n	$\rho$	$P_{\mathrm{avg}}$
1/6	1	1	DeepJSCC-TDMA	1	1/6	1
			DeepJSCC-PNOMA	1	1/6	1
				2	2/6	1/2
				4	4/6	1/4
				8	8/6	1/8
				16	16/6	1/16

TABLE II: Employed hyperparameters for fair comparison between scenarios with different number of users

Fig. 7: Comparison with NOMA-based methods for different bandwidth ratios on CIFAR-10 [ 51 ] .

Fig. 8: Performance comparison in terms of PSNRon AWGNand Rayleigh channels for correlated source images from Cityscapes dataset.

Fig. 9: Comparison of DeepJSCC-PNOMA with number of users

n\in\left\{1,2,4,8,16\right\}

Method	# Users	$\bar{\rho}=1/6$	$\bar{\rho}=1/12$
DeepJSCC-TDMA	All	$22\,200\,211$	$22\,149\,011$
DeepJSCC-PNOMA (Ours)	$1$	$22\,200\,211$	$22\,149\,011$
	$2$	$22\,202\,259$	$22\,149\,523$
	$4$	$22\,208\,403$	$22\,151\,059$
	$8$	$22\,232\,979$	$22\,157\,203$
	$16$	$22\,331\,283$	$22\,181\,779$

TABLE III: Number of trainable model parameters

Fig. 10: Ablation study of the number of the sampled training pairs and the introduced components.

Fig. 11: Analysis of orthogonality between transmitted filters on Kodak.

Panel of Figure 17 — Fig. 12: Qualitative comparison of reconstructed images.

Fig. 13: Visualization of transmitted filters for DeepJSCC-TDMA and DeepJSCC-PNOMA.

Fig. 14: Visualization of losses throughout the training or fine-tuning steps.

		SNR (dB)
Bandwidth	Users	0	3	7	10
Ratio
$\bar{\rho}=1/6$	$n=16$	25.96	28.37	31.28	33.27
	$n=32$	26.03	28.42	31.33	33.32
	$n=64$	26.05	28.46	31.34	33.29
$\bar{\rho}=1/12$	$n=16$	23.04	25.07	27.49	29.03

TABLE IV: Scalability analysis: Performance comparison on CIFAR-10 under AWGN channel for different bandwidth ratios. Values shown as PSNR (dB). Bold values indicate best performance within each bandwidth ratio group.

Method	$\bar{\rho}=\nicefrac{{1}}{{6}}$	$\bar{\rho}=\nicefrac{{1}}{{12}}$	$\bar{\rho}=\nicefrac{{1}}{{6}}$	$\bar{\rho}=\nicefrac{{1}}{{12}}$
	Training Duration		Number of Epochs
DeepJSCC-PNOMA ( $n=1$ )	1:04:38	1:50:16	54	80
DeepJSCC-PNOMA ( $n=2$ )	4:42:27	2:09:58	86	40
DeepJSCC-PNOMA ( $n=4$ )	3:49:57	2:34:43	42	28
DeepJSCC-PNOMA ( $n=8$ )	10:41:58	7:14:31	31	21
DeepJSCC-PNOMA ( $n=16$ )	20:24:06	3:40:45	33	11

TABLE V: Training durations and number of epochs passed before early stopping. Duration format is hours:minutes:seconds.

Fig. 15: Analysis of fairness between users on Kodak dataset.

Fig. 16: Comparison with point-to-point DeepJSCC and separation-based methods over SSIM, MS-SSIM and LPIPS metrics.

Fig. 17: Comparison with point-to-point DeepJSCC and separation-based methods with capacity over PSNR, SSIM, MS-SSIM and LPIPS metrics.

Fig. 18: Performance comparison in terms of MS-SSIMand LPIPSon AWGNand Rayleigh channels for correlated source images from Cityscapes dataset.

Fig. 19: Comparison of DeepJSCC-PNOMA for number of active users

|{{\cal P}}|\in\left\{1,2,4,8,16\right\}

to demonstrate the comprehensiveness of our method according to the Definition 2 .

Wireless Communications

Wireless communications studies how information is sent over radio links and how networks manage signals, spectrum, and resources reliably.

See all 400 papers

Diffusion-OAMP for Joint Image Compression and Wireless Transmission
Apr 30, 2026Wentao Hou, Yimin Bai, Zelei Luo +2Joint Source-Channel Coding Learned Image Compression
College of Information Science and Electronic Engineering, Zhejiang University, China
Joint Semantic-Channel Coding and Modulation for Generative Image Transmission
Oct 21, 2026Hao Cao, Jingkai Ying, Yinhuan Huang +2Joint Source-Channel Coding Deep Joint Source-Channel Coding
Department of Electronic Engineering, Tsinghua University · State Key Laboratory of Space Network and Communications
Deep Learning-Based Multi-User Communication Design for Dense IoT Networks: Interference-Aware Finite-Blocklength Communication and Preliminary MIMO Extensions
Aug 24, 2026Arkadeep Sinha, Shubham Paul, R. ManivasakanInternet of Things Wireless Communications
Indian Institute of Technology Madras

Apr 30, 2026J/K move · Enter open · S save

Diffusion-OAMP for Joint Image Compression and Wireless Transmission

Wentao Hou, Yimin Bai, Zelei Luo, Jiadong Hong+1

College of Information Science and Electronic Engineering, Zhejiang University, China

Joint Source-Channel Coding Learned Image Compression

Open paper AskPDF arXiv

Joint image compression and wireless transmission remain relatively underexplored compared to generic image restoration, despite its importance in practical communication systems. We formulate this problem under an equivalent linear model, and propose Diffusion-OAMP, a training-free reconstruction framework that embeds a pre-trained diffusion model into the OAMP algorithm. In Diffusion-OAMP, the OAMP linear estimator produces pseudo-AWGN observations, while the diffusion model serves as a nonlinear estimator under an SNR-matching rule. This framework offers a way to incorporate multiple generative priors into OAMP. Experiments with varying compression ratios and noise levels show that Diffusion-OAMP performs favorably against classic methods in the evaluated settings.

Abstract

Wireless Communications

Explore similar work

Diffusion-OAMP for Joint Image Compression and Wireless Transmission

Joint Semantic-Channel Coding and Modulation for Generative Image Transmission

Deep Learning-Based Multi-User Communication Design for Dense IoT Networks: Interference-Aware Finite-Blocklength Communication and Preliminary MIMO Extensions