A Spectral Viewpoint on Continual Relation Extraction

Huy Nguyen, Chien Nguyen, Linh Ngo, Anh Luu, Thien Nguyen


Abstract
Continual Relation Extraction (CRE) aims to continuously train a model to learn new relations while preserving its ability on previously learned relations. Similar to other continual learning problems, in CRE, models experience representation shift, where learned deep space changes in the continual learning process, which leads to the downgrade in the performance of the old tasks. In this work, we will provide an insight into this phenomenon under the spectral viewpoint. Our key argument is that, for each class shape, if its eigenvectors (or spectral components) do not change much, the shape is well-preserved. We then conduct a spectral experiment and show that, for the shape of each class, the eigenvectors with larger eigenvalue are more preserved after learning new tasks which means these vectors are good at keeping class shapes. Based on this analysis, we propose a simple yet effective class-wise regularization that improve the eigenvalues in the representation learning. We observe that our proposed regularization leads to an increase in the eigenvalues. Extensive experiments on two benchmark datasets, FewRel and TACRED, show the effectiveness of our proposed method with significant improvement in performance compared to the state-of-the-art models. Further analyses also verify our hypothesis that larger eigenvalues lead to better performance and vice versa.
Anthology ID:
2023.findings-emnlp.645
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9621–9629
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.645
DOI:
10.18653/v1/2023.findings-emnlp.645
Bibkey:
Cite (ACL):
Huy Nguyen, Chien Nguyen, Linh Ngo, Anh Luu, and Thien Nguyen. 2023. A Spectral Viewpoint on Continual Relation Extraction. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9621–9629, Singapore. Association for Computational Linguistics.
Cite (Informal):
A Spectral Viewpoint on Continual Relation Extraction (Nguyen et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.645.pdf