Skip to content

Latest commit

 

History

History
34 lines (23 loc) · 2.74 KB

File metadata and controls

34 lines (23 loc) · 2.74 KB

Back to https://github.com/Kwangkee/FL


Papers

[MAML-based FL Personalization]

Etc

FedABC: Targeting Fair Competition in Personalized Federated Learning, https://arxiv.org/abs/2302.07450


DFML

DFML: Dynamic Federated Meta-Learning for Rare Disease Prediction, https://scholar.google.co.kr/scholar?hl=ko&as_sdt=0%2C5&q=DFML%3A+Dynamic+Federated+Meta-Learning+for+Rare+Disease+Prediction&btnG=

  • Inspired by the framework (original federated meta-learning) in [12] described above, we utilize DFML to pre-dict rare diseases and apply two additional techniques to bolster its performance. We propose a novel dynamic weight-based fusion strategy and an inaccuracy-focused mechanism based on federated meta-learning for rare dis-ease prediction.
  • [12] F Chen, M Luo, Z Dong, et al, “Federated meta-learning with fast convergence and efficient communication.” arXiv preprint arXiv:1802.07876, 2018.
  • Some researchers use federated meta-learn-ing for personalized research [31], [32], [33], unlike feder-ated learning which focuses on the common output of all users.
  • [31] A Fallah, A Mokhtari, A Ozdaglar, “Personalized federated learning: A meta-learning approach.” arXiv preprint arXiv:2002.07948, 2020.
  • [32] Jiang, Y., Konečný, J., Rush, K, et al. "Improving federated learn-ing personalization via model agnostic meta learning." arXiv pre-print arXiv:1909.12488 ,2019.
  • [33] Fallah, A., Mokhtari, A. and Ozdaglar, A., “Personalized feder-ated learning with theoretical guarantees: A model-agnostic meta-learning approach.” Advances in Neural Information Pro-cessing Systems, 33, pp.3557-3568, 2020.

Back to the Top
Back to https://github.com/Kwangkee/FL