# Enhancing Continual Relation Extraction via Classifier Decomposition

arXiv: https://arxiv.org/abs/2305.04636 · HTML: https://mlsanity.com/paper/2305.04636/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 8 May 2023.

## Builds on (most cited first, 8 of 8)

- [FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation](https://mlsanity.com/paper/1810.10147/) (2018)
- [Sentence Embedding Alignment for Lifelong Relation Extraction](https://mlsanity.com/paper/1903.02588/) (2019)
- [Curriculum-Meta Learning for Order-Robust Continual Relation Extraction](https://mlsanity.com/paper/2101.01926/) (2021)
- [Consistent Representation Learning for Continual Relation Extraction](https://mlsanity.com/paper/2203.02721/) (2022)
- [Improving Continual Relation Extraction through Prototypical Contrastive Learning](https://mlsanity.com/paper/2210.04513/) (2022)
- [Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation](https://mlsanity.com/paper/2210.04497/) (2022)
- [Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification](https://mlsanity.com/paper/2108.12844/) (2021)
- [Less is More: Rethinking State-of-the-art Continual Relation Extraction Models with a Frustratingly Easy but Effective Approach](https://mlsanity.com/paper/2209.00243/) (2022)

## Built on by (most cited first, 8 of 8)

- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Towards Lifelong Learning of Large Language Models: A Survey](https://mlsanity.com/paper/2406.06391/) (2024)
- [Learning Wisdom from Errors: Promoting LLM's Continual Relation Learning through Exploiting Error Cases](https://mlsanity.com/paper/2508.12031/) (2025)
- [DP-CRE: Continual Relation Extraction via Decoupled Contrastive Learning and Memory Structure Preservation](https://mlsanity.com/paper/2403.02718/) (2024)
- [RepCL: Exploring Effective Representation for Continual Text Classification](https://mlsanity.com/paper/2305.07289/) (2023)
- [Balancing the Causal Effects in Class-Incremental Learning](https://mlsanity.com/paper/2402.10063/) (2024)
- [WAVE++: Capturing Within-Task Variance for Continual Relation Extraction with Adaptive Prompting](https://mlsanity.com/paper/2505.13944/) (2025)
- [Post-Training Language Models for Continual Relation Extraction](https://mlsanity.com/paper/2504.05214/) (2025)

## Abstract (arXiv)

Continual relation extraction (CRE) models aim at handling emerging new relations while avoiding catastrophically forgetting old ones in the streaming data. Though improvements have been shown by previous CRE studies, most of them only adopt a vanilla strategy when models first learn representations of new relations. In this work, we point out that there exist two typical biases after training of this vanilla strategy: classifier bias and representation bias, which causes the previous knowledge that the model learned to be shaded. To alleviate those biases, we propose a simple yet effective classifier decomposition framework that splits the last FFN layer into separated previous and current classifiers, so as to maintain previous knowledge and encourage the model to learn more robust representations at this training stage. Experimental results on two standard benchmarks show that our proposed framework consistently outperforms the state-of-the-art CRE models, which indicates that the importance of the first training stage to CRE models may be underestimated. Our code is available at https://github.com/hemingkx/CDec.