ModuleNet: Knowledge-inherited Neural Architecture Search

TL;DR

ModuleNet introduces a knowledge-inherited neural architecture search method that decomposes existing models into modules, enabling efficient architecture search and improved performance without retraining weights.

Contribution

The paper proposes a novel NAS algorithm that leverages existing model modules and their weights, enabling direct macro space search without weight tuning.

Findings

Achieves better performance on CIFAR datasets.

Efficiently evaluates architectures without weight tuning.

Utilizes inherited knowledge for improved search results.

Abstract

Although Neural Architecture Search (NAS) can bring improvement to deep models, they always neglect precious knowledge of existing models. The computation and time costing property in NAS also means that we should not start from scratch to search, but make every attempt to reuse the existing knowledge. In this paper, we discuss what kind of knowledge in a model can and should be used for new architecture design. Then, we propose a new NAS algorithm, namely ModuleNet, which can fully inherit knowledge from existing convolutional neural networks. To make full use of existing models, we decompose existing models into different \textit{module}s which also keep their weights, consisting of a knowledge base. Then we sample and search for new architecture according to the knowledge base. Unlike previous search algorithms, and benefiting from inherited knowledge, our method is able to directly search for architectures in the macro space by NSGA-II algorithm without tuning parameters in these \textit{module}s. Experiments show that our strategy can efficiently evaluate the performance of new architecture even without tuning weights in convolutional layers. With the help of knowledge we inherited, our search results can always achieve better performance on various datasets (CIFAR10, CIFAR100) over original architectures.