Consistent Representation Learning for Continual Relation Extraction
This work addresses the challenge of maintaining performance on old relations while learning new ones in continual relation extraction, which is crucial for real-world applications with evolving data, though it is incremental as it builds on existing memory-based approaches.
The paper tackles the problem of catastrophic forgetting in continual relation extraction by proposing a consistent representation learning method that uses contrastive learning and knowledge distillation during memory replay. The method significantly outperforms state-of-the-art baselines on FewRel and TACRED datasets, demonstrating strong robustness on imbalanced datasets.
Continual relation extraction (CRE) aims to continuously train a model on data with new relations while avoiding forgetting old ones. Some previous work has proved that storing a few typical samples of old relations and replaying them when learning new relations can effectively avoid forgetting. However, these memory-based methods tend to overfit the memory samples and perform poorly on imbalanced datasets. To solve these challenges, a consistent representation learning method is proposed, which maintains the stability of the relation embedding by adopting contrastive learning and knowledge distillation when replaying memory. Specifically, supervised contrastive learning based on a memory bank is first used to train each new task so that the model can effectively learn the relation representation. Then, contrastive replay is conducted of the samples in memory and makes the model retain the knowledge of historical relations through memory knowledge distillation to prevent the catastrophic forgetting of the old task. The proposed method can better learn consistent representations to alleviate forgetting effectively. Extensive experiments on FewRel and TACRED datasets show that our method significantly outperforms state-of-the-art baselines and yield strong robustness on the imbalanced dataset.