Network Architecture Search and specifically Regularized Evolution is a
common way to refine the structure of a deep learning model.However, little is
known about how models empirically evolve over time which has design
implications for designing caching policies, refining the search algorithm for
particular applications, and other important use cases.In this work, we
algorithmically analyze and quantitatively characterize the patterns of model
evolution for a set of models from the Candle project and the Nasbench-201
search space.We show how the evolution of the model structure is influenced by
the regularized evolution algorithm. We describe how evolutionary patterns
appear in distributed settings and opportunities for caching and improved
scheduling. Lastly, we describe the conditions that affect when particular
model architectures rise and fall in popularity based on their frequency of
acting as a donor in a sliding window.

对于 Candle 项目和 Nasbench-201 搜索空间中的一组模型，我们算法性地分析和定量地表征模型演化的模式。我们展示了模型结构的演化如何受到正则化进化算法的影响，描述了演化模式在分布式环境中的出现以及缓存和改进调度的机会。最后，我们描述了影响特定模型架构在流动窗口中作为供体的频率，从而影响模型架构的流行程度的条件。

深度学习模型进化在网络架构搜索中的模式理解

Understanding Patterns of Deep Learning ModelEvolution in Network  Architecture Search

Graph classification, which aims to identify the category labels of graphs,
plays a significant role in drug classification, toxicity detection, protein
analysis etc. However, the limitation of scale of benchmark datasets makes it
easy for graph classification models to fall into over-fitting and
undergeneralization. Towards this, we introduce data augmentation on graphs and
present two heuristic algorithms: random mapping and motif-similarity mapping,
to generate more weakly labeled data for small-scale benchmark datasets via
heuristic modification of graph structures. Furthermore, we propose a generic
model evolution framework, M-Evolve, which combines graph augmentation, data
filtration and model retraining to optimize pre-trained graph classifiers.
Experiments conducted on six benchmark datasets demonstrate that M-Evolve helps
existing graph classification models alleviate over-fitting when training on
small-scale benchmark datasets and yields an average improvement of 3-12%
accuracy on graph classification tasks.

该篇研究提出了两种启发式算法：随机映射和基元相似度映射，并结合数据增强、数据筛选和模型重训练的通用模型演化框架 M-Evolve 以优化预训练的图分类器，解决小规模基准数据集上过拟合问题，平均提高 3-12% 图分类任务的准确率。