Abstract
Transformer-based pre-trained models have emerged as the predominant solution for natural language processing (NLP). Fine-tuning such pre-trained models for downstream tasks often requires a considerable amount of labeled private data. In practice, private data is often distributed across heterogeneous mobile devices and may be prohibited from being uploaded. Moreover, well-curated labeled data is often scarce, presenting an additional challenge. To address these challenges, we first introduce a data generator for federated few-shot learning tasks, which encompasses the quantity and skewness of scarce labeled data in a realistic setting. Subsequently, we propose AUG-FedPrompt, a prompt-based federated learning system that exploits abundant unlabeled data for data augmentation. Our experiments indicate that AUG-FedPrompt can perform on par with full-set fine-tuning with a limited amount of labeled data. However, such competitive performance comes at a significant system cost.
Funding Information
  • National Key Research and Development Program of China (2020YFB1805500)
  • the Fundamental Research Funds for the Central Universities
  • NSFC (62032003, 61922017, 61921003, 62102045)
  • Beijing Nova Program (Z211100002121118)
  • Young Elite Scientists Sponsorship Program by CAST (2021QNRC001)