FedKD-hybrid: Federated Hybrid Knowledge Distillation for Lithography Hotspot Detection
This work addresses a domain-specific problem in semiconductor manufacturing by enhancing privacy-preserving machine learning for hotspot detection, though it appears incremental as it builds on existing federated learning and knowledge distillation techniques.
The paper tackles the problem of improving federated learning for lithography hotspot detection by proposing FedKD-hybrid, which combines parameter and knowledge distillation methods to better utilize learned information, achieving superior performance compared to state-of-the-art methods on ICCAD-2012 and FAB datasets.
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