# Budget-Aware Pruning for Multi-Domain Learning

arXiv: https://arxiv.org/abs/2210.08101 · HTML: https://mlsanity.com/paper/2210.08101/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 14 Oct 2022.

## Builds on (most cited first, 10 of 10)

- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Efficient parametrization of multi-domain deep neural networks](https://mlsanity.com/paper/1803.10082/) (2018)
- [Group Fisher Pruning for Practical Network Compression](https://mlsanity.com/paper/2108.00708/) (2021)
- [Learning to Balance Specificity and Invariance for In and Out of Domain Generalization](https://mlsanity.com/paper/2008.12839/) (2020)
- [Task Adaptive Parameter Sharing for Multi-Task Learning](https://mlsanity.com/paper/2203.16708/) (2022)
- [Adding New Tasks to a Single Network with Weight Transformations using Binary Masks](https://mlsanity.com/paper/1805.11119/) (2018)
- [Budget-Aware Adapters for Multi-Domain Learning](https://mlsanity.com/paper/1905.06242/) (2019)
- [DA3:Dynamic Additive Attention Adaption for Memory-EfficientOn-Device Multi-Domain Learning](https://mlsanity.com/paper/2012.01362/) (2020)
- [Boosting Binary Masks for Multi-Domain Learning through Affine Transformations](https://mlsanity.com/paper/2103.13894/) (2021)

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

- [Budget-Aware Pruning: Handling Multiple Domains with Less Parameters](https://mlsanity.com/paper/2309.11464/) (2023)

## Abstract (arXiv)

Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant amount of parameters. Such requirements hinder the use in resource-limited environments and demand both software and hardware optimization. Another limitation is that deep models are usually specialized into a single domain or task, requiring them to learn and store new parameters for each new one. Multi-Domain Learning (MDL) attempts to solve this problem by learning a single model that is capable of performing well in multiple domains. Nevertheless, the models are usually larger than the baseline for a single domain. This work tackles both of these problems: our objective is to prune models capable of handling multiple domains according to a user defined budget, making them more computationally affordable while keeping a similar classification performance. We achieve this by encouraging all domains to use a similar subset of filters from the baseline model, up to the amount defined by the user's budget. Then, filters that are not used by any domain are pruned from the network. The proposed approach innovates by better adapting to resource-limited devices while, to our knowledge, being the only work that is capable of handling multiple domains at test time with fewer parameters and lower computational complexity than the baseline model for a single domain.