Continuous Relation Extraction (CRE) aims to incrementally learn relation
knowledge from a non-stationary stream of data. Since the introduction of new
relational tasks can overshadow previously learned information, catastrophic
forgetting becomes a significant challenge in this domain. Current replay-based
training paradigms prioritize all data uniformly and train memory samples
through multiple rounds, which would result in overfitting old tasks and
pronounced bias towards new tasks because of the imbalances of the replay set.
To handle the problem, we introduce the DecouPled CRE (DP-CRE) framework that
decouples the process of prior information preservation and new knowledge
acquisition. This framework examines alterations in the embedding space as new
relation classes emerge, distinctly managing the preservation and acquisition
of knowledge. Extensive experiments show that DP-CRE significantly outperforms
other CRE baselines across two datasets.

DecouPled CRE (DP-CRE) framework effectively handles the challenge of catastrophic forgetting in Continuous Relation Extraction (CRE) by decoupling the preservation of prior information and acquisition of new knowledge, outperforming other CRE baselines in extensive experiments.