Structured Masked Diffusion for Joint Multiuser Decoding

Taekyun Lee, Jiyoung Yun, Jeffrey Andrews, Hyeji Kim

Keywords: Masked diffusion model, Wireless communication, Error correction coding, Generative model, Unsourced Random Access, Tanner graph, Parallel decoding

TL;DR: CIDER is a masked-diffusion outer decoder for unsourced random access that assembles AMP evidence into code-consistent message sets more reliably and over 70 times faster than SIC-style decoding.

Abstract: In joint multiuser decoding, a receiver recovers a set of messages from a single noisy aggregate of many simultaneous transmissions. Classical decoders rely on rule-based mechanisms such as successive interference cancellation, joint belief propagation, or list recovery, all of which become brittle or expensive as ambiguity increases. We propose CIDER, a learned multiuser decoder with masked-diffusion refinement steps. CIDER uses demixing to prevent duplicate-row collapse and uses parity-aware propagation to provide soft guidance from the code constraints. In higher-load regimes, we further improve reliability via a lightweight quality-guided remasking step that selectively re-decodes low-confidence sequences. On commonly used error correcting codes, CIDER matches or improves on FFT-accelerated joint belief propagation-style decoding in symbol error rate while running more than $6\times$ to over $100\times$ faster, with the speedup widening as the blocklength grows. Code is available at https://anonymous.4open.science/r/CIDER_2026/

Submission Number: 23