Kernel-Level Energy-Efficient Neural Architecture Search for Tabular Dataset

Many studies estimate energy consumption using proxy metrics like memory usage, FLOPs, and inference latency, with the assumption that reducing these metrics will also lower energy consumption in neural networks. This paper, however, takes a different approach by introducing an energy-efficient Neural Architecture Search (NAS) method that directly focuses on identifying architectures that minimize energy consumption while maintaining acceptable accuracy. Unlike previous methods that primarily target vision and language tasks, the approach proposed here specifically addresses tabular datasets. Remarkably, the optimal architecture suggested by this method can reduce energy consumption by up to 92% compared to architectures recommended by conventional NAS. Keywords: Neural Architecture Search Energy-Efficient NAS Energy Consumption Prediction. 1 Introduction Tabular datasets are among the oldest and most widely used types of datasets in practice, appearing in various fields such as medicine, finance, environmental science, and more. Alongside tree-based machine learning techniques, neural networks are a popular method for tackling tasks involving tabular data.