Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification

Tianyi Lei, Honghui Hu, Qiaoyang Luo, Dezhong Peng, Xu Wang


Abstract
Few-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect of matching between the few amount of samples and complicated models, as well as the distinction between useful and useless task features, these methods suffer from the overfitting issue. To address this issue, we propose a novel Adaptive Meta-learner via Gradient Similarity (AMGS) method to improve the model generalization ability to a new task. Specifically, the proposed AMGS alleviates the overfitting based on two aspects: (i) acquiring the potential semantic representation of samples and improving model generalization through the self-supervised auxiliary task in the inner loop, (ii) leveraging the adaptive meta-learner via gradient similarity to add constraints on the gradient obtained by base-learner in the outer loop. Moreover, we make a systematic analysis of the influence of regularization on the entire framework. Experimental results on several benchmarks demonstrate that the proposed AMGS consistently improves few-shot text classification performance compared with the state-of-the-art optimization-based meta-learning approaches. The code is available at: https://github.com/Tianyi-Lei.
Anthology ID:
2022.coling-1.431
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:
4873–4882
Language:
URL:
https://aclanthology.org/2022.coling-1.431
DOI:
Bibkey:
Cite (ACL):
Tianyi Lei, Honghui Hu, Qiaoyang Luo, Dezhong Peng, and Xu Wang. 2022. Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4873–4882, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification (Lei et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.431.pdf