Meta-Learning with Parameter Scaling for Cross-Domain Few-Shot Classification on GLUE under Adversarial Attacks

Meta-learning model can quickly adapt to new tasks using few-shot labeled data. However, despite achieving good generalization on few-shot classification tasks, it is still challenging to improve the adversarial robustness of the meta-learning model in few-shot learning. Although adversarial training (AT) methods such as Adversarial Query (AQ) can improve the adversarially robust performance of meta-learning models, AT is still computationally expensive training. On the other hand, meta-learning models trained with AT will drop significant accuracy on the original clean images. This paper prop

Research goal: To what extent does meta-learning with parameter scaling improve cross-domain generalization of few-shot classifiers on the GLUE benchmark under adversarial attacks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.3/10.