# Transfer learning for ensembles: reducing computation time and keeping the diversity

arXiv: https://arxiv.org/abs/2206.13116 · HTML: https://mlsanity.com/paper/2206.13116/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 27 Jun 2022.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs](https://mlsanity.com/paper/1802.10026/) (2018)
- [Deep Ensembles: A Loss Landscape Perspective](https://mlsanity.com/paper/1912.02757/) (2019)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [Snapshot Ensembles: Train 1, get M for free](https://mlsanity.com/paper/1704.00109/) (2017)
- [Training independent subnetworks for robust prediction](https://mlsanity.com/paper/2010.06610/) (2020)
- [Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors](https://mlsanity.com/paper/2005.07186/) (2020)
- [Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks](https://mlsanity.com/paper/1511.06314/) (2015)
- [Gradient Boosting Neural Networks: GrowNet](https://mlsanity.com/paper/2002.07971/) (2020)
- [Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?](https://mlsanity.com/paper/1806.07550/) (2018)
- [Deep Sub-Ensembles for Fast Uncertainty Estimation in Image Classification](https://mlsanity.com/paper/1910.08168/) (2019)
- [Deep Ensembles for Low-Data Transfer Learning](https://mlsanity.com/paper/2010.06866/) (2020)
- [Efficient Diversity-Driven Ensemble for Deep Neural Networks](https://mlsanity.com/paper/2112.13316/) (2021)
- [Landmark-Aware and Part-based Ensemble Transfer Learning Network for Facial Expression Recognition from Static images](https://mlsanity.com/paper/2104.11274/) (2021)
- [Embedded Ensembles: Infinite Width Limit and Operating Regimes](https://mlsanity.com/paper/2202.12297/) (2022)

## Built on by (most cited first, 1 of 1)

- [Socrates Loss: Unifying Confidence Calibration and Classification by Leveraging the Unknown](https://mlsanity.com/paper/2604.12245/) (2026)

## Abstract (arXiv)

Transferring a deep neural network trained on one problem to another requires only a small amount of data and little additional computation time. The same behaviour holds for ensembles of deep learning models typically superior to a single model. However, a transfer of deep neural networks ensemble demands relatively high computational expenses. The probability of overfitting also increases. Our approach for the transfer learning of ensembles consists of two steps: (a) shifting weights of encoders of all models in the ensemble by a single shift vector and (b) doing a tiny fine-tuning for each individual model afterwards. This strategy leads to a speed-up of the training process and gives an opportunity to add models to an ensemble with significantly reduced training time using the shift vector. We compare different strategies by computation time, the accuracy of an ensemble, uncertainty estimation and disagreement and conclude that our approach gives competitive results using the same computation complexity in comparison with the traditional approach. Also, our method keeps the ensemble's models' diversity higher.