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

TL;DR

This paper introduces Mod-CL, a self-supervised contrastive learning framework that leverages intra-instance modulation consistency to improve automatic modulation classification, especially with limited labeled data.

Contribution

It proposes a task-aware self-supervised method that constructs positive pairs from different segments of the same signal, aligning representations with modulation semantics.

Findings

Mod-CL outperforms baseline methods on RadioML datasets.

It achieves higher linear probing accuracy in low-label scenarios.

The approach effectively suppresses nuisance variations like noise and channel effects.

Abstract

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.