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

arXiv: https://arxiv.org/abs/2204.06625 · HTML: https://mlsanity.com/paper/2204.06625/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 50 references that are in the map.
- First posted on arXiv 13 Apr 2022.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization](https://mlsanity.com/paper/1911.03437/) (2019)
- [Massively Multilingual Neural Machine Translation](https://mlsanity.com/paper/1903.00089/) (2019)
- [Scaling Neural Machine Translation](https://mlsanity.com/paper/1806.00187/) (2018)
- [Knowledge Distillation by On-the-Fly Native Ensemble](https://mlsanity.com/paper/1806.04606/) (2018)
- [Better Fine-Tuning by Reducing Representational Collapse](https://mlsanity.com/paper/2008.03156/) (2020)
- [Online Knowledge Distillation with Diverse Peers](https://mlsanity.com/paper/1912.00350/) (2019)
- [Multi-task Sequence to Sequence Learning](https://mlsanity.com/paper/1511.06114/) (2015)
- [Universal Neural Machine Translation for Extremely Low Resource Languages](https://mlsanity.com/paper/1802.05368/) (2018)
- [Peer Collaborative Learning for Online Knowledge Distillation](https://mlsanity.com/paper/2006.04147/) (2020)
- [DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation](https://mlsanity.com/paper/2101.05544/) (2021)
- [Feature Fusion for Online Mutual Knowledge Distillation](https://mlsanity.com/paper/1904.09058/) (2019)
- [The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/2002.07972/) (2020)
- [Online Knowledge Distillation via Multi-branch Diversity Enhancement](https://mlsanity.com/paper/2010.00795/) (2020)

## Built on by (most cited first, 6 of 6)

- [Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling](https://mlsanity.com/paper/2210.05043/) (2022)
- [A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness](https://mlsanity.com/paper/2312.01082/) (2023)
- [DE3-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks](https://mlsanity.com/paper/2402.05948/) (2024)
- [Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation](https://mlsanity.com/paper/2406.12471/) (2024)
- [Cooperative Meta-Learning with Gradient Augmentation](https://mlsanity.com/paper/2406.04639/) (2024)
- [SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable](https://mlsanity.com/paper/2503.10881/) (2025)

## Abstract (arXiv)

Model ensemble is a popular approach to produce a low-variance and well-generalized model. However, it induces large memory and inference costs, which are 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).