A Novel Evolutionary Algorithm for Hierarchical Neural Architecture Search
This addresses the problem of efficient neural architecture search for machine learning practitioners, but appears incremental as it builds on existing evolutionary approaches.
The paper tackles neural architecture search by proposing a novel evolutionary algorithm with hierarchical modules and a curation system, achieving 93.2% accuracy on Fashion-MNIST and 94.8% on NAS-Bench101 in a small number of generations.
In this work, we propose a novel evolutionary algorithm for neural architecture search, applicable to global search spaces. The algorithm's architectural representation organizes the topology in multiple hierarchical modules, while the design process exploits this representation, in order to explore the search space. We also employ a curation system, which promotes the utilization of well performing sub-structures to subsequent generations. We apply our method to Fashion-MNIST and NAS-Bench101, achieving accuracies of $93.2\%$ and $94.8\%$ respectively in a relatively small number of generations.