# Conceptual Expansion Neural Architecture Search (CENAS)

arXiv: https://arxiv.org/abs/2110.03144 · HTML: https://mlsanity.com/paper/2110.03144/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 7 Oct 2021.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Zero-Shot Learning -- The Good, the Bad and the Ugly](https://mlsanity.com/paper/1703.04394/) (2017)
- [Random Search and Reproducibility for Neural Architecture Search](https://mlsanity.com/paper/1902.07638/) (2019)
- [Genetic CNN](https://mlsanity.com/paper/1703.01513/) (2017)
- [Learning to Detect](https://mlsanity.com/paper/1805.07631/) (2018)
- [SpinalNet: Deep Neural Network with Gradual Input](https://mlsanity.com/paper/2007.03347/) (2020)
- [Convolutional Neural Fabrics](https://mlsanity.com/paper/1606.02492/) (2016)
- [Conceptual Game Expansion](https://mlsanity.com/paper/2002.09636/) (2020)
- [Network Architecture Search for Domain Adaptation](https://mlsanity.com/paper/2008.05706/) (2020)
- [Combinets: Creativity via Recombination of Neural Networks](https://mlsanity.com/paper/1802.03605/) (2018)

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

- [Transfer Learning for Underrepresented Music Generation](https://mlsanity.com/paper/2306.00281/) (2023)

## Abstract (arXiv)

Architecture search optimizes the structure of a neural network for some task instead of relying on manual authoring. However, it is slow, as each potential architecture is typically trained from scratch. In this paper we present an approach called Conceptual Expansion Neural Architecture Search (CENAS) that combines a sample-efficient, computational creativity-inspired transfer learning approach with neural architecture search. This approach finds models faster than naive architecture search via transferring existing weights to approximate the parameters of the new model. It outperforms standard transfer learning by allowing for the addition of features instead of only modifying existing features. We demonstrate that our approach outperforms standard neural architecture search and transfer learning methods in terms of efficiency, performance, and parameter counts on a variety of transfer learning tasks.