A Tale of EDA's Long Tail: Long-Tailed Distribution Learning for Electronic Design Automation
A Tale of EDA's Long Tail: Long-Tailed Distribution Learning for Electronic Design Automation
复制标题
EDA 长尾故事：电子设计自动化的长尾分布学习
DOI：
10.1145/3551901.3556485
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Zixuan Jiang, Mingjie Liu
中科院分区：
文献类型：
--
作者：
Zixuan Jiang, Mingjie Liu
长尾分布是机器学习领域中一个普遍而关键的问题。虽然以前的工作解决了电子设计自动化(EDA)中几个任务中的数据不平衡问题，但现实中EDA问题中的长尾分布问题没有得到足够的重视。在这篇文章中，我们认为传统的性能指标可能具有误导性，特别是在EDA环境中。通过使用卷积神经网络和图神经网络的两个公开的EDA问题，我们证明了简单而有效的模型不可知的方法可以缓解机器学习算法在EDA中应用时由长尾分布引起的问题。
Long-tailed distribution is a common and critical issue in the field of machine learning. While prior work addressed data imbalance in several tasks in electronic design automation (EDA), insufficient attention has been paid to the long-tailed distribution in real-world EDA problems. In this paper, we argue that conventional performance metrics can be misleading, especially in EDA contexts. Through two public EDA problems using convolutional neural networks and graph neural networks, we demonstrate that simple yet effective model-agnostic methods can alleviate the issue induced by long-tailed distribution when applying machine learning algorithms in EDA.