Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915968599457792 |
|---|---|
| author | Li, Yuqi Lin, Xingyou Li, Yanli Zhang, Kai Yang, Chuanguang Guo, Zhongliang Gou, Jianping Huang, Tingwen Tian, Yingli |
| author_facet | Li, Yuqi Lin, Xingyou Li, Yanli Zhang, Kai Yang, Chuanguang Guo, Zhongliang Gou, Jianping Huang, Tingwen Tian, Yingli |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04066 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection Li, Yuqi Lin, Xingyou Li, Yanli Zhang, Kai Yang, Chuanguang Guo, Zhongliang Gou, Jianping Huang, Tingwen Tian, Yingli Machine Learning Hardware Architecture 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. |
| title | Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection |
| topic | Machine Learning Hardware Architecture |
| url | https://arxiv.org/abs/2501.04066 |