# Modulation Consistency-based Contrastive Learning for Self-Supervised Automatic Modulation Classification

arXiv: https://arxiv.org/abs/2605.11875 · HTML: https://mlsanity.com/paper/2605.11875/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 39 references that are in the map.
- First posted on arXiv 12 May 2026.

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

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Convolutional Radio Modulation Recognition Networks](https://mlsanity.com/paper/1602.04105/) (2016)
- [Distributed Deep Learning Models for Wireless Signal Classification with Low-Cost Spectrum Sensors](https://mlsanity.com/paper/1707.08908/) (2017)
- [Real-Time Radio Technology and Modulation Classification via an LSTM Auto-Encoder](https://mlsanity.com/paper/2011.08295/) (2020)
- [SigNet: A Novel Deep Learning Framework for Radio Signal Classification](https://mlsanity.com/paper/2011.03525/) (2020)
- [Self-Contrastive Learning based Semi-Supervised Radio Modulation Classification](https://mlsanity.com/paper/2203.15932/) (2022)
- [Revolution of Wireless Signal Recognition for 6G: Recent Advances, Challenges and Future Directions](https://mlsanity.com/paper/2503.08091/) (2025)

## Abstract (arXiv)

Deep learning-based AMC methods have achieved remarkable performance, but their practical deployment remains constrained by the high cost of labeled data. Although self-supervised learning (SSL) reduces the reliance on labels, existing SSL-based AMC methods often rely on task-agnostic pretext objectives misaligned with modulation classification, leading to representations entangled with nuisance factors such as symbol, channel, and noise. In this paper, we identify intra-instance modulation consistency as a task-aware structural prior, whereby different temporal segments of the same signal may differ in waveform while preserving the same modulation type, thus providing a principled cue for task-aligned self-supervision. Based on this prior, we propose Mod-CL, a Modulation consistency-based Contrastive Learning framework that constructs positive pairs from different temporal segments of the same signal instance, to encourage the model to learn shared modulation information while suppressing nuisance variations. We further develop a contrastive objective tailored to Mod-CL, which jointly exploits temporal segmentation and data augmentation to pull together views sharing the same modulation semantics while avoiding supervisory conflicts within each signal instance. Extensive experiments on RadioML datasets show that Mod-CL consistently outperforms strong baselines, especially in low-label regimes, achieving substantial improvements in linear probing accuracy.