Dynamic-prototype Contrastive Fine-tuning for Continual Few-shot Relation Extraction with Unseen Relation Detection

Si Miao Zhao, Zhen Tan, Ning Pang, Wei Dong Xiao, Xiang Zhao


Abstract
Continual Few-shot Relation Extraction (CFRE) aims to continually learn new relations from limited labeled data while preserving knowledge about previously learned relations. Facing the inherent issue of catastrophic forgetting, previous approaches predominantly rely on memory replay strategies. However, they often overlook task interference in continual learning and the varying memory requirements for different relations. To address these shortcomings, we propose a novel framework, DPC-FT, which features: 1) a lightweight relation encoder for each task to mitigate negative knowledge transfer across tasks; 2) a dynamic prototype module to allocate less memory for easier relations and more memory for harder relations. Additionally, we introduce the None-Of-The-Above (NOTA) detection in CFRE and propose a threshold criterion to identify relations that have never been learned. Extensive experiments demonstrate the effectiveness and efficiency of our method in CFRE, making our approach more practical and comprehensive for real-world scenarios.
Anthology ID:
2025.coling-main.586
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8763–8773
Language:
URL:
https://aclanthology.org/2025.coling-main.586/
DOI:
Bibkey:
Cite (ACL):
Si Miao Zhao, Zhen Tan, Ning Pang, Wei Dong Xiao, and Xiang Zhao. 2025. Dynamic-prototype Contrastive Fine-tuning for Continual Few-shot Relation Extraction with Unseen Relation Detection. In Proceedings of the 31st International Conference on Computational Linguistics, pages 8763–8773, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Dynamic-prototype Contrastive Fine-tuning for Continual Few-shot Relation Extraction with Unseen Relation Detection (Zhao et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.586.pdf