论文标题
跨传感器的神经建筑搜索的景观：它们有多大不同？
Landscape of Neural Architecture Search across sensors: how much do they differ ?
论文作者
论文摘要
随着神经建筑搜索的快速崛起，可以从搜索算法的角度理解其复杂性的能力。最近，Traoré等。已经提出了健身景观足迹的框架，以帮助描述和比较神经体系结构搜索问题。它试图描述为什么搜索策略可能成功，挣扎或失败目标任务。我们的研究在跨传感器（包括传感器数据融合）搜索的背景下利用了这种方法。特别是，我们将健身景观足迹应用于SO2SAT LCZ42的实际图像分类问题，以确定我们神经网络超参数优化问题的最有益的传感器。从健身分布的角度来看，我们的发现表明，所有传感器的搜索空间的类似行为：训练时间越长，整体适应度越大，景观中的整体适应性越大（坚固性和偏差）。关于传感器，其启用的健身越好（Sentinel-2），搜索轨迹越好（更顺畅，持久性越高）。结果还表明，对于搜索空间（Sentinel-2和Fusion）可以很好地拟合的传感器的搜索行为非常相似。
With the rapid rise of neural architecture search, the ability to understand its complexity from the perspective of a search algorithm is desirable. Recently, Traoré et al. have proposed the framework of Fitness Landscape Footprint to help describe and compare neural architecture search problems. It attempts at describing why a search strategy might be successful, struggle or fail on a target task. Our study leverages this methodology in the context of searching across sensors, including sensor data fusion. In particular, we apply the Fitness Landscape Footprint to the real-world image classification problem of So2Sat LCZ42, in order to identify the most beneficial sensor to our neural network hyper-parameter optimization problem. From the perspective of distributions of fitness, our findings indicate a similar behaviour of the search space for all sensors: the longer the training time, the larger the overall fitness, and more flatness in the landscapes (less ruggedness and deviation). Regarding sensors, the better the fitness they enable (Sentinel-2), the better the search trajectories (smoother, higher persistence). Results also indicate very similar search behaviour for sensors that can be decently fitted by the search space (Sentinel-2 and fusion).
