DUSE: A Data Expansion Framework for Low-resource Automatic Modulation Recognition based on Active Learning
This addresses data scarcity in automatic modulation recognition, a domain-specific problem, with incremental improvements over existing methods.
The paper tackles the problem of scarce labeled data for automatic modulation recognition by introducing DUSE, a data expansion framework that uses active learning to select useful samples from existing datasets, achieving consistent performance improvements over 8 baselines in both balanced and imbalanced settings.
Although deep neural networks have made remarkable achievements in the field of automatic modulation recognition (AMR), these models often require a large amount of labeled data for training. However, in many practical scenarios, the available target domain data is scarce and difficult to meet the needs of model training. The most direct way is to collect data manually and perform expert annotation, but the high time and labor costs are unbearable. Another common method is data augmentation. Although it can enrich training samples to a certain extent, it does not introduce new data and therefore cannot fundamentally solve the problem of data scarcity. To address these challenges, we introduce a data expansion framework called Dynamic Uncertainty-driven Sample Expansion (DUSE). Specifically, DUSE uses an uncertainty scoring function to filter out useful samples from relevant AMR datasets and employs an active learning strategy to continuously refine the scorer. Extensive experiments demonstrate that DUSE consistently outperforms 8 coreset selection baselines in both class-balance and class-imbalance settings. Besides, DUSE exhibits strong cross-architecture generalization for unseen models.