• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Parallel and Distributed Systems >A Distributed Framework for EA-Based NAS
【24h】

A Distributed Framework for EA-Based NAS

机译：基于EA的NAS分布式框架

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Evolutionary Algorithms (EA) are widely applied in Neural Architecture Search (NAS) and have achieved appealing results. Different EA-based NAS algorithms may utilize different encoding schemes for network representation, while they have the same workflow. Specifically, the first step is the initialization of the population with different encoding schemes, and the second step is the evaluation of the individuals by the fitness function. Then, the EA-based NAS algorithm executes evolution operations, e.g., selection, mutation, and crossover, to eliminate weak individuals and generate more competitive ones. Lastly, evolution continues until the max generation and the best neural architectures will be chosen. Because each individual needs complete training and validation on the target dataset, the EA-based NAS always consumes significant computation and time inevitably, which results in the bottleneck of this approach. To ameliorate this issue, this article proposes a distributed framework to boost the computation of the EA-based NAS algorithm. This framework is a server/worker model where the server distributes individuals requested by the computing nodes and collects the validated individuals and hosts the evolution operations. Meanwhile, the most time-consuming phase (i.e., individual evaluation) of the EA-based NAS is allocated to the computing nodes, which send requests asynchronously to the server and evaluate the fitness values of the individuals. Additionally, a new packet structure of the message delivered in the cluster is designed to encapsulate various network representations and support different EA-based NAS algorithms. We design an EA-based NAS algorithm as a case to investigate the efficiency of the proposed framework. Extensive experiments are performed on an illustrative cluster with different scales, and the results reveal that the framework can achieve a nearly linear reduction of the search time with the increase of the computational nodes. Furthermore, the length of the exchanged messages among the cluster is tiny, which benefits the framework expansion.
机译：进化算法（EA）广泛应用于神经结构搜索（NAS）并实现了吸引力的结果。基于EA的NAS算法可以利用不同的网络表示编码方案，而它们具有相同的工作流程。具体地，第一步是具有不同编码方案的群体的初始化，第二步骤是通过适应功能对各个的评估。然后，基于EA的NAS算法执行演化操作，例如选择，突变和交叉，以消除弱者并产生更具竞争力的。最后，进化仍在继续，直到最大的生成和最佳的神经架构将被选中。因为每个人都需要在目标数据集上完成完整的培训和验证，所以基于EA的NAS总是不可避免地消耗大量的计算和时间，这导致这种方法的瓶颈。为了改善这个问题，本文提出了一个分布式框架，以提高基于EA的NAS算法的计算。此框架是服务器/工作型号的服务器/工作型号，服务器分配计算节点请求的个体，并收集已验证的个人并托管演进操作。同时，基于EA的NAS的最耗时的阶段（即单个评估）被分配给计算节点，该计算节点将异步发送到服务器并评估个人的适应值。另外，群集中传送的消息的新数据包结构被设计为封装各种网络表示并支持基于EA的NAS算法。我们设计基于EA的NAS算法，以研究提出框架的效率。在具有不同尺度的说明性集群上进行广泛的实验，结果表明，框架可以随着计算节点的增加实现搜索时间的几乎线性减少。此外，群集中交换消息的长度是小的，这有利于框架扩展。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号