Contents

Federated Learning

Contents

Federated Learning

連合学習は、サーバとクライアント間でデータでなくモデルパラメータの差分のみをやり取りすることで、モデル全体の性能を向上させる手法である[McMahan et al., 2017]。

医療や金融などデータのプライバシー保護が重要となる分野では、連合学習が有用である[Roth et al., 2020]。

また、量子データに対する”量子連合学習”も提案されている[Chehimi and Saad, 2021]。

References

MMR+17

H. Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Agüera \noopsort arcasy Arcas. Communication-Efficient Learning of Deep Networks from Decentralized Data. arXiv:1602.05629 [cs], February 2017. Comment: This version updates the large-scale LSTM experiments, along with other minor changes. In earlier versions, an inconsistency in our implementation of FedSGD caused us to report much lower learning rates for the large-scale LSTM. We reran these experiments, and also found that fewer local epochs offers better performance, leading to slightly better results for FedAvg than previously reported. URL: http://arxiv.org/abs/1602.05629 (visited on 2021-06-14), arXiv:1602.05629.

RCS+20

Holger R. Roth, Ken Chang, Praveer Singh, Nir Neumark, Wenqi Li, Vikash Gupta, Sharut Gupta, Liangqiong Qu, Alvin Ihsani, Bernardo C. Bizzo, Yuhong Wen, Varun Buch, Meesam Shah, Felipe Kitamura, Matheus Mendonça, Vitor Lavor, Ahmed Harouni, Colin Compas, Jesse Tetreault, Prerna Dogra, Yan Cheng, Selnur Erdal, Richard White, Behrooz Hashemian, Thomas Schultz, Miao Zhang, Adam McCarthy, B. Min Yun, Elshaimaa Sharaf, Katharina V. Hoebel, Jay B. Patel, Bryan Chen, Sean Ko, Evan Leibovitz, Etta D. Pisano, Laura Coombs, Daguang Xu, Keith J. Dreyer, Ittai Dayan, Ram C. Naidu, Mona Flores, Daniel Rubin, and Jayashree Kalpathy-Cramer. Federated Learning for Breast Density Classification: A Real-World Implementation. arXiv:2009.01871 [cs, eess], 12444:181–191, 2020. Comment: Accepted at the 1st MICCAI Workshop on "Distributed And Collaborative Learning"; add citation to Fig. 1 & 2 and update Fig. 5; fix typo in affiliations. URL: http://arxiv.org/abs/2009.01871 (visited on 2021-06-14), arXiv:2009.01871.

CS21

Mahdi Chehimi and Walid Saad. Quantum Federated Learning with Quantum Data. arXiv:2106.00005 [quant-ph], May 2021. Comment: 13 pages, 5 figures. URL: http://arxiv.org/abs/2106.00005 (visited on 2021-06-02), arXiv:2106.00005.

Federated Learning

連合学習は、サーバとクライアント間でデータでなくモデルパラメータの差分のみをやり取りすることで、モデル全体の性能を向上させる手法である[McMahan et al., 2017]。

医療や金融などデータのプライバシー保護が重要となる分野では、連合学習が有用である[Roth et al., 2020]。

また、量子データに対する”量子連合学習”も提案されている[Chehimi and Saad, 2021]。

References

MMR+17

H. Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Agüera \noopsort arcasy Arcas. Communication-Efficient Learning of Deep Networks from Decentralized Data. arXiv:1602.05629 [cs], February 2017. Comment: This version updates the large-scale LSTM experiments, along with other minor changes. In earlier versions, an inconsistency in our implementation of FedSGD caused us to report much lower learning rates for the large-scale LSTM. We reran these experiments, and also found that fewer local epochs offers better performance, leading to slightly better results for FedAvg than previously reported. URL: http://arxiv.org/abs/1602.05629 (visited on 2021-06-14), arXiv:1602.05629.

RCS+20

Holger R. Roth, Ken Chang, Praveer Singh, Nir Neumark, Wenqi Li, Vikash Gupta, Sharut Gupta, Liangqiong Qu, Alvin Ihsani, Bernardo C. Bizzo, Yuhong Wen, Varun Buch, Meesam Shah, Felipe Kitamura, Matheus Mendonça, Vitor Lavor, Ahmed Harouni, Colin Compas, Jesse Tetreault, Prerna Dogra, Yan Cheng, Selnur Erdal, Richard White, Behrooz Hashemian, Thomas Schultz, Miao Zhang, Adam McCarthy, B. Min Yun, Elshaimaa Sharaf, Katharina V. Hoebel, Jay B. Patel, Bryan Chen, Sean Ko, Evan Leibovitz, Etta D. Pisano, Laura Coombs, Daguang Xu, Keith J. Dreyer, Ittai Dayan, Ram C. Naidu, Mona Flores, Daniel Rubin, and Jayashree Kalpathy-Cramer. Federated Learning for Breast Density Classification: A Real-World Implementation. arXiv:2009.01871 [cs, eess], 12444:181–191, 2020. Comment: Accepted at the 1st MICCAI Workshop on "Distributed And Collaborative Learning"; add citation to Fig. 1 & 2 and update Fig. 5; fix typo in affiliations. URL: http://arxiv.org/abs/2009.01871 (visited on 2021-06-14), arXiv:2009.01871.

CS21

Mahdi Chehimi and Walid Saad. Quantum Federated Learning with Quantum Data. arXiv:2106.00005 [quant-ph], May 2021. Comment: 13 pages, 5 figures. URL: http://arxiv.org/abs/2106.00005 (visited on 2021-06-02), arXiv:2106.00005.

previous

Differential Privacy

next

Storage capacity of a simple perceptron