论文标题
使用图神经网络的神经体系结构性能预测
Neural Architecture Performance Prediction Using Graph Neural Networks
论文作者
论文摘要
在计算机视觉研究中，自动化建筑工程的过程，神经体系结构搜索（NAS）引起了极大的兴趣。由于计算成本很高，最新的NAS方法以及少数可用的基准仅提供有限的搜索空间。在本文中，我们提出了一个基于图神经网络（GNN）的神经体系结构性能预测的替代模型。我们通过评估NAS-Bench-101数据集中的多个实验中的GNN来证明该替代模型对结构未知架构（即零射击预测）的神经体系结构性能预测的有效性。
In computer vision research, the process of automating architecture engineering, Neural Architecture Search (NAS), has gained substantial interest. Due to the high computational costs, most recent approaches to NAS as well as the few available benchmarks only provide limited search spaces. In this paper we propose a surrogate model for neural architecture performance prediction built upon Graph Neural Networks (GNN). We demonstrate the effectiveness of this surrogate model on neural architecture performance prediction for structurally unknown architectures (i.e. zero shot prediction) by evaluating the GNN on several experiments on the NAS-Bench-101 dataset.
