SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning

Thanh-Thien Le, Viet Dao, Linh Nguyen, Thi-Nhung Nguyen, Linh Ngo, Thien Nguyen


Abstract
Continual event detection is a cornerstone in uncovering valuable patterns in many dynamic practical applications, where novel events emerge daily. Existing state-of-the-art approaches with replay buffers still suffer from catastrophic forgetting, partially due to overly simplistic objective aggregation. This oversight disregards complex trade-offs and leads to sub-optimal gradient updates, resulting in performance deterioration across objectives. While there are successful, widely cited multi-objective optimization frameworks for multi-task learning, they lack mechanisms to address data imbalance and evaluate whether a Pareto-optimal solution can effectively mitigate catastrophic forgetting, rendering them unsuitable for direct application to continual learning. To address these challenges, we propose **SharpSeq**, a novel continual learning paradigm leveraging sharpness-aware minimization combined with a generative model to balance training data distribution. Through extensive experiments on multiple real-world datasets, we demonstrate the superior performance of SharpSeq in continual event detection, proving the importance of our approach in mitigating catastrophic forgetting in continual event detection.
Anthology ID:
2024.naacl-long.200
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3632–3644
Language:
URL:
https://aclanthology.org/2024.naacl-long.200
DOI:
Bibkey:
Cite (ACL):
Thanh-Thien Le, Viet Dao, Linh Nguyen, Thi-Nhung Nguyen, Linh Ngo, and Thien Nguyen. 2024. SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3632–3644, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning (Le et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.200.pdf
Copyright:
 2024.naacl-long.200.copyright.pdf