FedKD-hybrid: Federated Hybrid Knowledge Distillation for Lithography Hotspot Detection

2025-01-07

AI Summary

To address lithographic hotspot detection (LHD) under distributed privacy-preserving settings, this paper proposes a novel federated learning paradigm integrating parameter sharing and knowledge distillation. The method introduces the first federated hybrid knowledge distillation framework for LHD: it simultaneously uploads both model-layer parameters and logits from clients, while leveraging a shared public dataset to bridge cross-client knowledge alignment and complementary knowledge transfer. This design eliminates raw data transmission, ensuring privacy compliance while enabling efficient collaborative training. Experiments on the ICCAD-2012 benchmark and real-world FAB datasets demonstrate that the proposed approach achieves 3.2–5.8% higher detection accuracy than state-of-the-art federated methods and accelerates convergence by approximately 40%.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Security and Privacy: Privacy-enhancing technologies

Abstract

Federated Learning (FL) provides novel solutions for machine learning (ML)-based lithography hotspot detection (LHD) under distributed privacy-preserving settings. Currently, two research pipelines have been investigated to aggregate local models and achieve global consensus, including parameter/nonparameter based (also known as knowledge distillation, namely KD). While these two kinds of methods show effectiveness in specific scenarios, we note they have not fully utilized and transferred the information learned, leaving the potential of FL-based LDH remains unexplored. Thus, we propose FedKDhybrid in this study to mitigate the research gap. Specifically, FedKD-hybrid clients agree on several identical layers across all participants and a public dataset for achieving global consensus. During training, the trained local model will be evaluated on the public dataset, and the generated logits will be uploaded along with the identical layer parameters. The aggregated information is consequently used to update local models via the public dataset as a medium. We compare our proposed FedKD-hybrid with several state-of-the-art (SOTA) FL methods under ICCAD-2012 and FAB (real-world collected) datasets with different settings; the experimental results demonstrate the superior performance of the FedKD-hybrid algorithm. Our code is available at https://github.com/itsnotacie/NN-FedKD-hybrid

Problem

• Privacy Preservation
• Federated Learning
• Lithography Hotspot Detection

Innovation

• Federated Learning
• Knowledge Distillation
• Lithography Hotspot Detection