CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing

Chen Liang, Pengcheng He, Yelong Shen, Weizhu Chen, Tuo Zhao


Abstract
Model ensemble is a popular approach to produce a low-variance and well-generalized model. However, it induces large memory and inference costs, which is often not affordable for real-world deployment. Existing work has resorted to sharing weights among models. However, when increasing the proportion of the shared weights, the resulting models tend to be similar, and the benefits of using model ensemble diminish. To retain ensemble benefits while maintaining a low memory cost, we propose a consistency-regularized ensemble learning approach based on perturbed models, named CAMERO. Specifically, we share the weights of bottom layers across all models and apply different perturbations to the hidden representations for different models, which can effectively promote the model diversity. Meanwhile, we apply a prediction consistency regularizer across the perturbed models to control the variance due to the model diversity. Our experiments using large language models demonstrate that CAMERO significantly improves the generalization performance of the ensemble model. Specifically, CAMERO outperforms the standard ensemble of 8 BERT-base models on the GLUE benchmark by 0.7 with a significantly smaller model size (114.2M vs. 880.6M).
Anthology ID:
2022.acl-long.495
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7162–7175
Language:
URL:
https://aclanthology.org/2022.acl-long.495
DOI:
10.18653/v1/2022.acl-long.495
Bibkey:
Cite (ACL):
Chen Liang, Pengcheng He, Yelong Shen, Weizhu Chen, and Tuo Zhao. 2022. CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7162–7175, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing (Liang et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/author-url/2022.acl-long.495.pdf
Code
 cliang1453/camero
Data
CoLAGLUEMRPCMultiNLIQNLISST