HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking

TL;DR

HM-NAS introduces a hierarchical masking approach for neural architecture search, enabling more flexible architecture exploration and automatic learning of optimal structures, outperforming existing weight sharing methods.

Contribution

It proposes a hierarchical masking scheme and multi-level encoding to improve NAS flexibility and eliminate reliance on hand-designed heuristics.

Findings

HM-NAS achieves better search performance than state-of-the-art methods.

The searched architectures are more flexible and meaningful.

Models evaluated show competitive accuracy.

Abstract

The use of automatic methods, often referred to as Neural Architecture Search (NAS), in designing neural network architectures has recently drawn considerable attention. In this work, we present an efficient NAS approach, named HM- NAS, that generalizes existing weight sharing based NAS approaches. Existing weight sharing based NAS approaches still adopt hand-designed heuristics to generate architecture candidates. As a consequence, the space of architecture candidates is constrained in a subset of all possible architectures, making the architecture search results sub-optimal. HM-NAS addresses this limitation via two innovations. First, HM-NAS incorporates a multi-level architecture encoding scheme to enable searching for more flexible network architectures. Second, it discards the hand-designed heuristics and incorporates a hierarchical masking scheme that automatically learns and determines the optimal architecture. Compared to state-of-the-art weight sharing based approaches, HM-NAS is able to achieve better architecture search performance and competitive model evaluation accuracy. Without the constraint imposed by the hand-designed heuristics, our searched networks contain more flexible and meaningful architectures that existing weight sharing based NAS approaches are not able to discover.