arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.04066cs.LGcs.AR
收藏

联邦知识蒸馏用于多模型架构光刻热点检测

Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection

City University of New York（纽约城市大学）；Sichuan Agricultural University（四川农业大学）；The University of Sydney（悉尼大学）；Shenzhen University of Advanced Technology（深圳先进技术大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of St Andrews（圣安德鲁大学）；Southwest University（西南大学）

Yuqi Li, Xingyou Lin, Yanli Li, Kai Zhang, Chuanguang Yang, Zhongliang Guo, Jianping Gou, Tingwen Huang, Yingli Tian

备注：
Accept by ICME2026
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出FedKD-hybrid框架，结合参数聚合与知识蒸馏提升协同学习效果，在ICCAD-2012和真实FAB数据集上验证了其在有效性与鲁棒性上的优势。

摘要：

作为多媒体数据的一种特殊类型，光刻热点检测（LHD）训练通常需要比传统多媒体数据更强的隐私保护，而联邦学习提供了一个有前景的解决方案。然而，现有方法仅依赖参数聚合或知识蒸馏（KD），未能充分利用协同学习的潜力。为此，我们提出FedKD-hybrid，一种结合两种范式优势的新型框架。具体而言，FedKD-hybrid利用公共数据集达成共识，其中客户端交换已同意层的参数和logits。这种混合信息被聚合以优化本地模型，增强知识转移。在ICCAD-2012和真实世界FAB数据集上的广泛实验表明，FedKD-hybrid在有效性和鲁棒性上均优于现有最先进方法。

英文摘要：

As a special type of multimedia data, Lithography Hotspot Detection (LHD) training often requires stronger privacy protection than conventional multimedia data, and federated learning provides a promising potential solution to this challenge. However, existing approaches rely solely on either parameter aggregation or Knowledge Distillation (KD), failing to fully exploit the potential of collaborative learning. To address this, we propose FedKD-hybrid, a novel framework that synergizes the strengths of both paradigms. Specifically, FedKD-hybrid utilizes a public dataset to facilitate consensus, where clients exchange both parameters of agreed-upon layers and logits. This hybrid information is aggregated to refine local models, enhancing knowledge transfer. Extensive experiments on ICCAD-2012 and real-world FAB datasets demonstrate that FedKD-hybrid consistently outperforms state-of-the-art methods in both effectiveness and robustness.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑