Recent advancements in Artificial Intelligence (AI), driven by Neural Networks (NN), demand innovative neural architecture designs, particularly within the constrained environments of Internet of Things (IoT) systems, to balance performance and efficiency. HW-aware Neural Architecture Search (HW-aware NAS) emerges as an attractive strategy to automate the design of NN using multi-objective optimization approaches, such as evolutionary algorithms. However, the intricate relationship between NN design parameters and HW-aware NAS optimization objectives remains an underexplored research area, overlooking opportunities to effectively leverage this knowledge to guide the search process accordingly. Furthermore, the large amount of evaluation data produced during the search holds untapped potential for refining the optimization strategy and improving the approximation of the Pareto front. Addressing these issues, we propose SONATA, a self-adaptive evolutionary algorithm for HW-aware NAS. Our method leverages adaptive evolutionary operators guided by the learned importance of NN design parameters. Specifically, through tree-based surrogate models and a Reinforcement Learning agent, we aspire to gather knowledge on 'How' and 'When' to evolve NN architectures. Comprehensive evaluations across various NAS search spaces and hardware devices on the ImageNet-1k dataset have shown the merit of SONATA with up to 0.25% improvement in accuracy and up to 2.42x gains in latency and energy. Our SONATA has seen up to sim$93.6% Pareto dominance over the native NSGA-II, further stipulating the importance of self-adaptive evolution operators in HW-aware NAS.

翻译：近年来，由神经网络驱动的人工智能发展，特别是在物联网系统的资源受限环境中，亟需创新的神经架构设计，以平衡性能与效率。硬件感知神经架构搜索作为一种有吸引力的策略，利用多目标优化方法（如进化算法）自动化设计神经网络。然而，神经网络设计参数与硬件感知神经架构搜索优化目标之间的复杂关系仍是一个尚未充分探索的研究领域，未能有效利用这一知识来引导搜索过程。此外，搜索过程中产生的大量评估数据在优化策略细化及帕累托前沿逼近方面具有未被充分利用的潜力。针对这些问题，我们提出SONATA——一种用于硬件感知神经架构搜索的自适应进化算法。该方法通过由神经网络设计参数学习重要性引导的自适应进化算子，具体借助基于树的代理模型和强化学习代理，探索“如何”及“何时”进化神经网络架构。在ImageNet-1k数据集上，跨越多种搜索空间与硬件设备的综合评估表明，SONATA在准确率上提升高达0.25%，延迟与能耗上获得高达2.42倍的收益。我们的SONATA在帕累托支配性上相比原生NSGA-II达到高达93.6%的统治率，进一步证实了自适应进化算子在硬件感知神经架构搜索中的重要性。