Relational concept enhanced prototypical network for incremental few-shot relation classification

Rong Ma, Bo Ma, Lei Wang, Xi Zhou, Zhen Wang, Yating Yang

Abstract: Highlights•We propose a relational concept enhanced prototypical network to address incremental few-shot relation classification.•We propose a base-class augmented contrastive learning method for forgetting problems.•We propose incorporating relational concepts as external knowledge to alleviate the overfitting problem.•Our proposed model achieves better results compared to the baseline models.