ESM: A Framework for Building Effective Surrogate Models for Hardware-Aware Neural Architecture Search
This work addresses the need for efficient surrogate models in hardware-aware NAS for resource-constrained devices, but it appears incremental as it builds on existing methods with a focus on systematic analysis and framework development.
The paper tackles the problem of building effective latency prediction models for hardware-aware Neural Architecture Search (NAS) on GPU-powered devices, presenting a holistic framework based on systematic analysis of factors influencing prediction accuracy.
Hardware-aware Neural Architecture Search (NAS) is one of the most promising techniques for designing efficient Deep Neural Networks (DNNs) for resource-constrained devices. Surrogate models play a crucial role in hardware-aware NAS as they enable efficient prediction of performance characteristics (e.g., inference latency and energy consumption) of different candidate models on the target hardware device. In this paper, we focus on building hardware-aware latency prediction models. We study different types of surrogate models and highlight their strengths and weaknesses. We perform a systematic analysis to understand the impact of different factors that can influence the prediction accuracy of these models, aiming to assess the importance of each stage involved in the model designing process and identify methods and policies necessary for designing/training an effective estimation model, specifically for GPU-powered devices. Based on the insights gained from the analysis, we present a holistic framework that enables reliable dataset generation and efficient model generation, considering the overall costs of different stages of the model generation pipeline.