Classical Sequence Match Is a Competitive Few-Shot One-Class Learner

Mengting Hu, Hang Gao, Yinhao Bai, Mingming Liu


Abstract
Nowadays, transformer-based models gradually become the default choice for artificial intelligence pioneers. The models also show superiority even in the few-shot scenarios. In this paper, we revisit the classical methods and propose a new few-shot alternative. Specifically, we investigate the few-shot one-class problem, which actually takes a known sample as a reference to detect whether an unknown instance belongs to the same class. This problem can be studied from the perspective of sequence match. It is shown that with meta-learning, the classical sequence match method, i.e. Compare-Aggregate, significantly outperforms transformer ones. The classical approach requires much less training cost. Furthermore, we perform an empirical comparison between two kinds of sequence match approaches under simple fine-tuning and meta-learning. Meta-learning causes the transformer models’ features to have high-correlation dimensions. The reason is closely related to the number of layers and heads of transformer models. Experimental codes and data are available at https://github.com/hmt2014/FewOne.
Anthology ID:
2022.coling-1.419
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4728–4740
Language:
URL:
https://aclanthology.org/2022.coling-1.419
DOI:
Bibkey:
Cite (ACL):
Mengting Hu, Hang Gao, Yinhao Bai, and Mingming Liu. 2022. Classical Sequence Match Is a Competitive Few-Shot One-Class Learner. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4728–4740, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Classical Sequence Match Is a Competitive Few-Shot One-Class Learner (Hu et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.419.pdf
Code
 hmt2014/fewone