融合联邦学习与知识蒸馏，提升光刻热点检测隐私保护下的性能
Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection
- 结合参数聚合与知识蒸馏，通过公共数据集促进多方协作
- 在ICCAD-2012和真实工厂数据上优于现有方法，准确率更高且更稳定
- 适合需要隐私保护的半导体制造场景，尤其适用于多模型协同
光刻热点检测（LHD）作为一类特殊多媒体数据，其训练过程对隐私保护要求高于常规多媒体数据。联邦学习为该问题提供了有前景的解决方案。然而，现有方法仅依赖参数聚合或知识蒸馏（KD），未能充分挖掘协同学习潜力。为此，本文提出FedKD-hybrid框架，融合两种范式优势：利用公共数据集促进共识，客户端交换协商一致层的参数与软标签（logits），通过混合信息聚合优化本地模型，增强知识迁移。在ICCAD-2012和真实工厂（FAB）数据集上的大量实验表明，FedKD-hybrid在有效性和鲁棒性方面均持续优于当前最优方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。