NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search

by   Rameswar Panda, et al.

Neural Architecture Search (NAS) is an open and challenging problem in machine learning. While NAS offers great promise, the prohibitive computational demand of most of the existing NAS methods makes it difficult to directly search the architectures on large-scale tasks. The typical way of conducting large scale NAS is to search for an architectural building block on a small dataset (either using a proxy set from the large dataset or a completely different small scale dataset) and then transfer the block to a larger dataset. Despite a number of recent results that show the promise of transfer from proxy datasets, a comprehensive evaluation of different NAS methods studying the impact of different source datasets and training protocols has not yet been addressed. In this work, we propose to analyze the architecture transferability of different NAS methods by performing a series of experiments on large scale benchmarks such as ImageNet1K and ImageNet22K. We find that: (i) On average, transfer performance of architectures searched using completely different small datasets perform similarly to the architectures searched directly on proxy target datasets. However, design of proxy sets has considerable impact on rankings of different NAS methods. (ii) While the different NAS methods show similar performance on a source dataset (e.g., CIFAR10), they significantly differ on the transfer performance to a large dataset (e.g., ImageNet1K). (iii) Even on large datasets, the randomly sampled architecture baseline is very competitive and significantly outperforms many representative NAS methods. (iv) The training protocol has a larger impact on small datasets, but it fails to provide consistent improvements on large datasets. We believe that our NASTransfer benchmark will be key to designing future NAS strategies that consistently show superior transfer performance on large scale datasets.


page 7

page 12


Large Scale Neural Architecture Search with Polyharmonic Splines

Neural Architecture Search (NAS) is a powerful tool to automatically des...

EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search

Neural architecture search (NAS) methods have been proposed to release h...

NAS evaluation is frustratingly hard

Neural Architecture Search (NAS) is an exciting new field which promises...

Data Proxy Generation for Fast and Efficient Neural Architecture Search

Due to the recent advances on Neural Architecture Search (NAS), it gains...

Learned Transferable Architectures Can Surpass Hand-Designed Architectures for Large Scale Speech Recognition

In this paper, we explore the neural architecture search (NAS) for autom...

Neural Architectural Backdoors

This paper asks the intriguing question: is it possible to exploit neura...

β-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search

Neural Architecture Search has attracted increasing attention in recent ...

Please sign up or login with your details

Forgot password? Click here to reset