Semi-Supervised Hotspot Detection with Self-Paced Multi-Task Learning
Semi-Supervised Hotspot Detection with Self-Paced Multi-Task Learning
复制标题
DOI：
10.1145/3287624.3287685
复制
发表时间：
2019-01
期刊：
影响因子：
--
通讯作者：
Ying Chen;Yibo Lin;Tianyang Gai;Yajuan Su;Yayi Wei;D. Pan
中科院分区：
文献类型：
--
作者：
Ying Chen;Yibo Lin;Tianyang Gai;Yajuan Su;Yayi Wei;D. Pan
光刻模拟对于热点检测是计算上昂贵的。基于机器学习的热点检测是一种很有前途的减少仿真开销的技术。然而，大多数学习方法依赖于大量的训练数据来实现良好的准确性和通用性。在开发新技术节点的早期阶段，具有标记的热点或非热点的数据量非常有限。在本文中，我们提出了一个半监督热点检测与自定进度的多任务学习范式，利用两个数据样本w./ W.O.标签，以提高模型的准确性和通用性。实验结果表明，我们的方法可以实现2.9 - 4.5%的更好的准确率在相同的虚警水平比国家的最先进的工作使用10%-50%的训练数据。源代码和训练模型发布在www.example.com上。
Lithography simulation is computationally expensive for hotspot detection. Machine learning based hotspot detection is a promising technique to reduce the simulation overhead. However, most learning approaches rely on a large amount of training data to achieve good accuracy and generality. At the early stage of developing a new technology node, the amount of data with labeled hotspots or non-hotspots is very limited. In this paper, we propose a semi-supervised hotspot detection with self-paced multi-task learning paradigm, leveraging both data samples w./w.o. labels to improve model accuracy and generality. Experimental results demonstrate that our approach can achieve 2.9-4.5% better accuracy at the same false alarm levels than the state-of-the-art work using 10%-50% of training data. The source code and trained models are released on https://github.com/qwepi/SSL.