Efficient Multi-Objective Neural Architecture Search via Pareto Dominance-based Novelty Search
This work addresses efficiency and diversity challenges in NAS for researchers and practitioners, though it is incremental as it builds on existing novelty search and training-free metric approaches.
The paper tackles the problem of premature convergence and limited diversity in neural architecture search (NAS) by proposing MTF-PDNS, a method that uses novelty search based on multiple training-free metrics, resulting in improved convergence speed, diversity, transferability, and reduced computational costs compared to conventional objective-driven NAS methods.
Neural Architecture Search (NAS) aims to automate the discovery of high-performing deep neural network architectures. Traditional objective-based NAS approaches typically optimize a certain performance metric (e.g., prediction accuracy), overlooking large parts of the architecture search space that potentially contain interesting network configurations. Furthermore, objective-driven population-based metaheuristics in complex search spaces often quickly exhaust population diversity and succumb to premature convergence to local optima. This issue becomes more complicated in NAS when performance objectives do not fully align with the actual performance of the candidate architectures, as is often the case with training-free metrics. While training-free metrics have gained popularity for their rapid performance estimation of candidate architectures without incurring computation-heavy network training, their effective incorporation into NAS remains a challenge. This paper presents the Pareto Dominance-based Novelty Search for multi-objective NAS with Multiple Training-Free metrics (MTF-PDNS). Unlike conventional NAS methods that optimize explicit objectives, MTF-PDNS promotes population diversity by utilizing a novelty score calculated based on multiple training-free performance and complexity metrics, thereby yielding a broader exploration of the search space. Experimental results on standard NAS benchmark suites demonstrate that MTF-PDNS outperforms conventional methods driven by explicit objectives in terms of convergence speed, diversity maintenance, architecture transferability, and computational costs.