# A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognition

arXiv: https://arxiv.org/abs/2608.15160 · HTML: https://mlsanity.com/paper/2608.15160/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Convolutional Radio Modulation Recognition Networks](https://mlsanity.com/paper/1602.04105/) (2016)
- [Deep Architectures for Modulation Recognition](https://mlsanity.com/paper/1703.09197/) (2017)
- [Deep Learning Based Automatic Modulation Recognition: Models, Datasets, and Challenges](https://mlsanity.com/paper/2207.09647/) (2022)
- [ms-Mamba: Multi-scale Mamba for Time-Series Forecasting](https://mlsanity.com/paper/2504.07654/) (2025)
- [Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation](https://mlsanity.com/paper/2606.01048/) (2026)
- [STF-GCN: A Multi-Domain Graph Convolution Network Method for Automatic Modulation Recognition via Adaptive Correlation](https://mlsanity.com/paper/2504.08504/) (2025)
- [MCANet: A Coherent Multimodal Collaborative Attention Network for Advanced Modulation Recognition in Adverse Noisy Environments](https://mlsanity.com/paper/2510.18336/) (2025)

## Abstract (arXiv)

Automatic modulation recognition (AMR) faces distinct representation bottlenecks under varying observation lengths, where a single model architecture often fails to excel. To address this, we propose a unified backbone-expert framework with a common convolutional state-space backbone and two specialized interfaces. For short sequences, we inject explicit lag-aware complex-plane descriptors as relation tokens before encoding to compensate for information loss. For long sequences, we design a gated multi-scale residual refinement module to correct the feature map, combined with a fixed-averaging classifier collaboration to harness complementary evidence. Our framework achieves overall average accuracies of 67.28 ± 0.14% on RML2016.10b and 87.19 ± 0.77% on HisarMod2019 (mean ± sample standard deviation over three runs), respectively. The framework's efficacy is further validated through three-seed ablations, native-length cross-configuration tests, and controlled window studies, confirming the benefit of expert-interface decoupling over one-size-fits-all architectures.