Neural Architecture Search (NAS) methods are widely used in various
industries to obtain high quality taskspecific solutions with minimal human
intervention. Event Sequences find widespread use in various industrial
applications including churn prediction customer segmentation fraud detection
and fault diagnosis among others. Such data consist of categorical and
real-valued components with irregular timestamps. Despite the usefulness of NAS
methods previous approaches only have been applied to other domains images
texts or time series. Our work addresses this limitation by introducing a novel
NAS algorithm SeqNAS specifically designed for event sequence classification.
We develop a simple yet expressive search space that leverages commonly used
building blocks for event sequence classification including multihead self
attention convolutions and recurrent cells. To perform the search we adopt
sequential Bayesian Optimization and utilize previously trained models as an
ensemble of teachers to augment knowledge distillation. As a result of our work
we demonstrate that our method surpasses state of the art NAS methods and
popular architectures suitable for sequence classification and holds great
potential for various industrial applications.

我们的研究采用了一种新的神经架构搜索（NAS）算法 SeqNAS，针对事件序列分类问题，通过引入一个简单但表达能力强的搜索空间，利用常用的建模模块，如多头自注意力、卷积和循环单元，结合序贝叶斯优化算法以及先前的模型训练，我们的方法在超过了现有最先进的 NAS 方法和适用于序列分类的流行体系结构，展示了在各种工业应用中巨大的潜力。

SeqNAS：面向事件序列分类的神经体系结构搜索

SeqNAS: Neural Architecture Search for Event Sequence Classification

In this paper, we propose an efficient NAS algorithm for generating
task-specific models that are competitive under multiple competing objectives.
It comprises of two surrogates, one at the architecture level to improve sample
efficiency and one at the weights level, through a supernet, to improve
gradient descent training efficiency. On standard benchmark datasets (C10,
C100, ImageNet), the resulting models, dubbed NSGANetV2, either match or
outperform models from existing approaches with the search being orders of
magnitude more sample efficient. Furthermore, we demonstrate the effectiveness
and versatility of the proposed method on six diverse non-standard datasets,
e.g. STL-10, Flowers102, Oxford Pets, FGVC Aircrafts etc. In all cases,
NSGANetV2s improve the state-of-the-art (under mobile setting), suggesting that
NAS can be a viable alternative to conventional transfer learning approaches in
handling diverse scenarios such as small-scale or fine-grained datasets. Code
is available at this https URL

本文提出了一种高效的 NAS 算法，用于生成具有多个竞争目标的任务特定模型，在标准基准数据集上表现优异，且搜索效率大幅提高，并在六个不同的非标准数据集上证明了该方法的有效性和多样性。