Federated Few-Shot Learning for Mobile NLP
Dongqi Cai, Shangguang Wang, Yaozong Wu, Felix Xiaozhu Lin, Mengwei Xu
Abstract
Natural language processing (NLP) sees rich mobile applications. To support various language understanding tasks, a foundation NLP model is often fine-tuned in a federated, privacy-preserving setting (FL). This process currently relies on at least hundreds of thousands of labeled training samples from mobile clients; yet mobile users often lack willingness or knowledge to label their data. Such an inadequacy of data labels is known as a few-shot scenario; it becomes the key blocker for mobile NLP applications.
Topics & Concepts
Computer scienceArtificial intelligenceShot (pellet)Key (lock)Natural language processingProcess (computing)One shotLabeled dataComputer securityOrganic chemistryChemistryEngineeringMechanical engineeringOperating systemPrivacy-Preserving Technologies in DataMobile Crowdsensing and CrowdsourcingInternet Traffic Analysis and Secure E-voting