Cross Domain Few-Shot Learning via Meta Adversarial Training
This addresses a practical cross-domain challenge in few-shot learning for relation classification, though it appears incremental as it builds on existing prototypical networks with adversarial training.
The paper tackles the problem of few-shot relation classification when training and testing data come from different domains, proposing a meta-based adversarial training framework to adapt prototypical networks to target domain data, with empirical studies confirming its effectiveness.
Few-shot relation classification (RC) is one of the critical problems in machine learning. Current research merely focuses on the set-ups that both training and testing are from the same domain. However, in practice, this assumption is not always guaranteed. In this study, we present a novel model that takes into consideration the afore-mentioned cross-domain situation. Not like previous models, we only use the source domain data to train the prototypical networks and test the model on target domain data. A meta-based adversarial training framework (MBATF) is proposed to fine-tune the trained networks for adapting to data from the target domain. Empirical studies confirm the effectiveness of the proposed model.