Privacy-Preserving Federated Learning for Science

2026

  1. G. Byeon, M. Ryu, Z. W. Di, and K. Kim, “FIRM: Federated image reconstruction using multimodal tomographic data,” Computational Optimization and Applications, pp. 1–36, 2026.
    BibTeX 
    @article{byeon2026firm,
  title = {FIRM: Federated image reconstruction using multimodal tomographic data},
  author = {Byeon, Geunyeong and Ryu, Minseok and Di, Zichao Wendy and Kim, Kibaek},
  journal = {Computational Optimization and Applications},
  pages = {1--36},
  year = {2026},
  publisher = {Springer US New York}
}
  2. Y. Li et al., “Scalable Cross-Facility Federated Learning for Scientific Foundation Models on Multiple Supercomputers,” arXiv preprint arXiv:2603.19544, 2026.
    BibTeX 
    @article{li2026scalable,
  title = {Scalable Cross-Facility Federated Learning for Scientific Foundation Models on Multiple Supercomputers},
  author = {Li, Yijiang and Li, Zilinghan and Chard, Kyle and Foster, Ian and Munson, Todd and Madduri, Ravi and Kim, Kibaek},
  journal = {arXiv preprint arXiv:2603.19544},
  year = {2026}
}
  3. Y. Li, E. Dey, Z. Li, K. Raghavan, R. Madduri, and K. Kim, “FedQueue: Queue-Aware Federated Learning for Cross-Facility HPC Training,” arXiv preprint arXiv:2605.02125 (accepted to ICML 2026), 2026.
    BibTeX 
    @article{li2026fedqueue,
  title = {FedQueue: Queue-Aware Federated Learning for Cross-Facility HPC Training},
  author = {Li, Yijiang and Dey, Emon and Li, Zilinghan and Raghavan, Krishnan and Madduri, Ravi and Kim, Kibaek},
  journal = {arXiv preprint arXiv:2605.02125 (accepted to ICML 2026)},
  year = {2026}
}

2025

  1. Z. Li, S. He, Z. Yang, M. Ryu, K. Kim, and R. Madduri, “Advances in APPFL: A comprehensive and extensible federated learning framework,” in 2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid), 2025, pp. 01–11.
    BibTeX 
    @inproceedings{li2025advances,
  title = {Advances in APPFL: A comprehensive and extensible federated learning framework},
  author = {Li, Zilinghan and He, Shilan and Yang, Ze and Ryu, Minseok and Kim, Kibaek and Madduri, Ravi},
  booktitle = {2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)},
  pages = {01--11},
  year = {2025}
}
  2. G. Bai, Y. Li, Z. Li, L. Zhao, and K. Kim, “FedSpaLLM: Federated pruning of large language models,” in Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies (Volume 1: Long Papers), 2025.
    BibTeX 
    @inproceedings{bai2025fedspallm,
  title = {FedSpaLLM: Federated pruning of large language models},
  author = {Bai, Guangji and Li, Yijiang and Li, Zilinghan and Zhao, Liang and Kim, Kibaek},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL): Human Language Technologies (Volume 1: Long Papers)},
  year = {2025}
}
  3. Y. Qiu, K. Kim, and F. Yousefian, “A randomized zeroth-order hierarchical framework for heterogeneous federated learning,” in 2025 IEEE 64th Conference on Decision and Control (CDC), IEEE, 2025, pp. 605–610.
    BibTeX 
    @inproceedings{qiu2025randomized,
  title = {A randomized zeroth-order hierarchical framework for heterogeneous federated learning},
  author = {Qiu, Yuyang and Kim, Kibaek and Yousefian, Farzad},
  booktitle = {2025 IEEE 64th Conference on Decision and Control (CDC)},
  pages = {605--610},
  year = {2025},
  organization = {IEEE}
}
  4. M. Ebrahimi, U. V. Shanbhag, and F. Yousefian, “On the Resolution of Stochastic MPECs over Networks: Distributed Implicit Zeroth-Order Gradient Tracking Methods.” 2025. Available at: https://arxiv.org/abs/2505.22916
    BibTeX 
    @misc{ebrahimi2025resolutionstochasticmpecsnetworks,
  title = {On the Resolution of Stochastic MPECs over Networks: Distributed Implicit Zeroth-Order Gradient Tracking Methods},
  author = {Ebrahimi, Mohammadjavad and Shanbhag, Uday V. and Yousefian, Farzad},
  year = {2025},
  eprint = {2505.22916},
  archiveprefix = {arXiv},
  primaryclass = {math.OC},
  url = {https://arxiv.org/abs/2505.22916}
}
  5. J. Xu, R. Hu, and O. Kotevska, “Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy.” 2025. Available at: https://arxiv.org/abs/2505.13655
    BibTeX 
    @misc{xu2025optimalclientsamplingfederated,
  title = {Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy},
  author = {Xu, Jiahao and Hu, Rui and Kotevska, Olivera},
  year = {2025},
  eprint = {2505.13655},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2505.13655}
}
  6. J. Xu, R. Hu, O. Kotevska, and Z. Zhang, “Traceable Black-box Watermarks for Federated Learning.” 2025. Available at: https://arxiv.org/abs/2505.13651
    BibTeX 
    @misc{xu2025traceableblackboxwatermarksfederated,
  title = {Traceable Black-box Watermarks for Federated Learning},
  author = {Xu, Jiahao and Hu, Rui and Kotevska, Olivera and Zhang, Zikai},
  year = {2025},
  eprint = {2505.13651},
  archiveprefix = {arXiv},
  primaryclass = {cs.CR},
  url = {https://arxiv.org/abs/2505.13651}
}
  7. A. Sinha, Z. Li, T. Liu, V. Kindratenko, K. Kim, and R. Madduri, “Cost-Aware Federated Learning on the Cloud,” in 2025 IEEE International Conference on eScience (eScience), IEEE, 2025, pp. 321–322.
    BibTeX 
    @inproceedings{sinha2025cost,
  title = {Cost-Aware Federated Learning on the Cloud},
  author = {Sinha, Aditya and Li, Zilinghan and Liu, Tingkai and Kindratenko, Volodymyr and Kim, Kibaek and Madduri, Ravi},
  booktitle = {2025 IEEE International Conference on eScience (eScience)},
  pages = {321--322},
  year = {2025},
  organization = {IEEE}
}
  8. A. Van Nguyen, D. Klabjan, M. Ryu, K. Kim, and Z. Di, “Federated Low-Rank Tensor Estimation for Multimodal Image Reconstruction,” in 2025 International Joint Conference on Neural Networks (IJCNN), IEEE, 2025, pp. 1–8.
    BibTeX 
    @inproceedings{van2025federated,
  title = {Federated Low-Rank Tensor Estimation for Multimodal Image Reconstruction},
  author = {Van Nguyen, Anh and Klabjan, Diego and Ryu, Minseok and Kim, Kibaek and Di, Zichao},
  booktitle = {2025 International Joint Conference on Neural Networks (IJCNN)},
  pages = {1--8},
  year = {2025},
  organization = {IEEE}
}
  9. T.-H. Hoang et al., “Enabling end-to-end secure federated learning in biomedical research on heterogeneous computing environments with APPFLx,” Computational and Structural Biotechnology Journal, vol. 28, pp. 29–39, 2025.
    BibTeX 
    @article{hoang2025enabling,
  title = {Enabling end-to-end secure federated learning in biomedical research on heterogeneous computing environments with APPFLx},
  author = {Hoang, Trung-Hieu and Fuhrman, Jordan and Klarqvist, Marcus and Li, Miao and Chaturvedi, Pranshu and Li, Zilinghan and Kim, Kibaek and Ryu, Minseok and Chard, Ryan and Huerta, Eliu A and others},
  journal = {Computational and Structural Biotechnology Journal},
  volume = {28},
  pages = {29--39},
  year = {2025},
  publisher = {Elsevier}
}
  10. Z. Li, A. Sinha, Y. Li, K. Chard, K. Kim, and R. Madduri, “Experiences Building Enterprise-Level Privacy-Preserving Federated Learning to Power AI for Science,” arXiv preprint arXiv:2511.08998, 2025.
    BibTeX 
    @article{li2025experiences,
  title = {Experiences Building Enterprise-Level Privacy-Preserving Federated Learning to Power AI for Science},
  author = {Li, Zilinghan and Sinha, Aditya and Li, Yijiang and Chard, Kyle and Kim, Kibaek and Madduri, Ravi},
  journal = {arXiv preprint arXiv:2511.08998},
  year = {2025}
}
  11. Z. Chen et al., “FedDES: Discrete Event Based Performance Simulation for Federated Learning Systems,” in Proceedings of the Tenth ACM/IEEE Symposium on Edge Computing, 2025, pp. 1–16.
    BibTeX 
    @inproceedings{chen2025feddes,
  title = {FedDES: Discrete Event Based Performance Simulation for Federated Learning Systems},
  author = {Chen, Zhonghao and Chen, Weicong and Zhang, Duo and Kim, Kibaek and Li, Guanpeng and Di, Sheng and Lu, Xiaoyi},
  booktitle = {Proceedings of the Tenth ACM/IEEE Symposium on Edge Computing},
  pages = {1--16},
  year = {2025}
}

2024

  1. R. Madduri, Z. Li, T. Nandi, K. Kim, M. Ryu, and A. Rodriguez, “Advances in Privacy Preserving Federated Learning to Realize a Truly Learning Healthcare System,” in 2024 IEEE 6th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA), IEEE, 2024, pp. 273–279.
    BibTeX 
    @inproceedings{madduri2024advances,
  title = {Advances in Privacy Preserving Federated Learning to Realize a Truly Learning Healthcare System},
  author = {Madduri, Ravi and Li, Zilinghan and Nandi, Tarak and Kim, Kibaek and Ryu, Minseok and Rodriguez, Alex},
  booktitle = {2024 IEEE 6th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA)},
  pages = {273--279},
  year = {2024},
  organization = {IEEE}
}
  2. K. Kim et al., “Privacy-Preserving Federated Learning for Science: Challenges and Research Directions,” in 2024 IEEE International Conference on Big Data (BigData), IEEE, 2024, pp. 7849–7853.
    BibTeX 
    @inproceedings{kim2024privacy,
  title = {Privacy-Preserving Federated Learning for Science: Challenges and Research Directions},
  author = {Kim, Kibaek and Raghavan, Krishnan and Kotevska, Olivera and Dorier, Matthieu and Madduri, Ravi and Ryu, Minseok and Munson, Todd and Ross, Rob and Flynn, Thomas and Kagawa, Ai and others},
  booktitle = {2024 IEEE International Conference on Big Data (BigData)},
  pages = {7849--7853},
  year = {2024},
  organization = {IEEE}
}
  3. T. Flynn, P. Johnstone, and S. Yoo, “Problem-dependent convergence bounds for randomized linear gradient compression.” 2024. Available at: https://arxiv.org/abs/2411.12898
    BibTeX 
    @misc{flynn2024problemdependentconvergenceboundsrandomized,
  title = {Problem-dependent convergence bounds for randomized linear gradient compression},
  author = {Flynn, Thomas and Johnstone, Patrick and Yoo, Shinjae},
  year = {2024},
  eprint = {2411.12898},
  archiveprefix = {arXiv},
  primaryclass = {math.OC},
  url = {https://arxiv.org/abs/2411.12898}
}
  4. H. F. Hamann et al., “Foundation models for the electric power grid,” Joule, vol. 8, no. 12, pp. 3245–3258, 2024.
    BibTeX 
    @article{hamann2024foundation,
  title = {Foundation models for the electric power grid},
  author = {Hamann, Hendrik F and Gjorgiev, Blazhe and Brunschwiler, Thomas and Martins, Leonardo SA and Puech, Alban and Varbella, Anna and Weiss, Jonas and Bernabe-Moreno, Juan and Mass{\'e}, Alexandre Blondin and Choi, Seong Lok and others},
  journal = {Joule},
  volume = {8},
  number = {12},
  pages = {3245--3258},
  year = {2024},
  publisher = {Elsevier}
}