virtual adversarial perturbation

Zuoyebang Tech Team

Nov 9, 2022 · Artificial Intelligence

Boost Data Annotation Efficiency with VAPAL: Active Learning Meets Virtual Adversarial Perturbation

This article explains how a pool‑based active learning framework that combines uncertainty sampling (using BADGE, ALPS, or virtual adversarial perturbations) with diversity‑driven clustering can dramatically cut labeling costs for Transformer‑based NLP models, and presents experimental results showing VAPAL’s competitive performance and early‑stage advantages.