# Task-Aware Neural Architecture Search

arXiv: https://arxiv.org/abs/2010.13962 · HTML: https://mlsanity.com/paper/2010.13962/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2020.

## Built on by (most cited first, 5 of 5)

- [Fisher Task Distance and Its Application in Neural Architecture Search](https://mlsanity.com/paper/2103.12827/) (2021)
- [Transfer Learning for Individual Treatment Effect Estimation](https://mlsanity.com/paper/2210.00380/) (2022)
- [Improving Open-Domain Dialogue Evaluation with a Causal Inference Model](https://mlsanity.com/paper/2301.13372/) (2023)
- [Improved Automated Machine Learning from Transfer Learning](https://mlsanity.com/paper/2103.00241/) (2021)
- [Mode-Aware Continual Learning for Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2305.11400/) (2023)

## Abstract (arXiv)

The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain knowledge and have generally used limited search spaces. In this paper, we propose a novel framework for neural architecture search, utilizing a dictionary of models of base tasks and the similarity between the target task and the atoms of the dictionary; hence, generating an adaptive search space based on the base models of the dictionary. By introducing a gradient-based search algorithm, we can evaluate and discover the best architecture in the search space without fully training the networks. The experimental results show the efficacy of our proposed task-aware approach.