Ensemble Making Few-Shot Learning Stronger
This work addresses the challenge of adapting single models to various relation learning tasks in few-shot settings, which is incremental as it builds on existing ensemble and attention methods.
The paper tackles the high variance problem in few-shot relation learning by proposing an ensemble approach with fine-tuning and feature attention strategies, achieving significant performance improvements over previous state-of-the-art models.
Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks. Many few-shot models have been widely used for relation learning tasks. However, each of these models has a shortage of capturing a certain aspect of semantic features, for example, CNN on long-range dependencies part, Transformer on local features. It is difficult for a single model to adapt to various relation learning, which results in the high variance problem. Ensemble strategy could be competitive on improving the accuracy of few-shot relation extraction and mitigating high variance risks. This paper explores an ensemble approach to reduce the variance and introduces fine-tuning and feature attention strategies to calibrate relation-level features. Results on several few-shot relation learning tasks show that our model significantly outperforms the previous state-of-the-art models.