FLAg: An automated client-independent federated learning system on HPC for digital pathology slice training

Yen Jung Chiu; Chao Chun Chuang; Yu Tai Wang; Lin Chi Yeh; Romel Edwardo Rudon; Kuan Wei Lin; Wei Jong Yang; Yang C. Fann; Pau Choo Chung

doi:10.1109/CAI54212.2023.00139

FLAg: An automated client-independent federated learning system on HPC for digital pathology slice training

Yen Jung Chiu^*, Chao Chun Chuang, Yu Tai Wang, Lin Chi Yeh, Romel Edwardo Rudon, Kuan Wei Lin, Wei Jong Yang, Yang C. Fann, Pau Choo Chung

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Federated Learning (FL) provides an approach for performing the collaborative training of AI models without compromising data privacy. However, traditional implementations of FL require complex deployment strategies, making it challenging to perform training across multiple data centers. To address this issue, this article presents a platform designated as Federated Learning Agent (FLAg) which allows users to delegate their federated learning tasks to an automated process. FLAg features digital pathology databases as well as multiple pretrained models. The security of FLAg is ensured through its deployment on an HPC system and bastion host. While FLAg itself only offers FL training services, users may perform data annotation and inference through its integration with a proprietary ALOVAS AI pathology platform for a complete end-to-end process which includes annotation, FL training, and inference.

Original language	English
Title of host publication	Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	314-315
Number of pages	2
ISBN (Electronic)	9798350339840
DOIs	https://doi.org/10.1109/CAI54212.2023.00139
State	Published - 2023
Externally published	Yes
Event	2023 IEEE Conference on Artificial Intelligence, CAI 2023 - Santa Clara, United States Duration: 05 06 2023 → 06 06 2023

Publication series

Name	Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023

Conference

Conference	2023 IEEE Conference on Artificial Intelligence, CAI 2023
Country/Territory	United States
City	Santa Clara
Period	05/06/23 → 06/06/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Federated Learning
High-performance computing
Inference
Pathology
Segmentation

Access to Document

10.1109/CAI54212.2023.00139

Cite this

Chiu, Y. J., Chuang, C. C., Wang, Y. T., Yeh, L. C., Edwardo Rudon, R., Lin, K. W., Yang, W. J., Fann, Y. C., & Chung, P. C. (2023). FLAg: An automated client-independent federated learning system on HPC for digital pathology slice training. In Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023 (pp. 314-315). (Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CAI54212.2023.00139

Chiu, Yen Jung ; Chuang, Chao Chun ; Wang, Yu Tai et al. / FLAg : An automated client-independent federated learning system on HPC for digital pathology slice training. Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 314-315 (Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023).

@inproceedings{fe134360cff7414e9d360387e0899d49,

title = "FLAg: An automated client-independent federated learning system on HPC for digital pathology slice training",

abstract = "Federated Learning (FL) provides an approach for performing the collaborative training of AI models without compromising data privacy. However, traditional implementations of FL require complex deployment strategies, making it challenging to perform training across multiple data centers. To address this issue, this article presents a platform designated as Federated Learning Agent (FLAg) which allows users to delegate their federated learning tasks to an automated process. FLAg features digital pathology databases as well as multiple pretrained models. The security of FLAg is ensured through its deployment on an HPC system and bastion host. While FLAg itself only offers FL training services, users may perform data annotation and inference through its integration with a proprietary ALOVAS AI pathology platform for a complete end-to-end process which includes annotation, FL training, and inference.",

keywords = "Federated Learning, High-performance computing, Inference, Pathology, Segmentation",

author = "Chiu, \{Yen Jung\} and Chuang, \{Chao Chun\} and Wang, \{Yu Tai\} and Yeh, \{Lin Chi\} and \{Edwardo Rudon\}, Romel and Lin, \{Kuan Wei\} and Yang, \{Wei Jong\} and Fann, \{Yang C.\} and Chung, \{Pau Choo\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Conference on Artificial Intelligence, CAI 2023 ; Conference date: 05-06-2023 Through 06-06-2023",

year = "2023",

doi = "10.1109/CAI54212.2023.00139",

language = "英语",

series = "Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "314--315",

booktitle = "Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023",

address = "美国",

}

Chiu, YJ, Chuang, CC, Wang, YT, Yeh, LC, Edwardo Rudon, R, Lin, KW, Yang, WJ, Fann, YC & Chung, PC 2023, FLAg: An automated client-independent federated learning system on HPC for digital pathology slice training. in Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023. Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023, Institute of Electrical and Electronics Engineers Inc., pp. 314-315, 2023 IEEE Conference on Artificial Intelligence, CAI 2023, Santa Clara, United States, 05/06/23. https://doi.org/10.1109/CAI54212.2023.00139

FLAg: An automated client-independent federated learning system on HPC for digital pathology slice training. / Chiu, Yen Jung; Chuang, Chao Chun; Wang, Yu Tai et al.
Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 314-315 (Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - FLAg

T2 - 2023 IEEE Conference on Artificial Intelligence, CAI 2023

AU - Chiu, Yen Jung

AU - Chuang, Chao Chun

AU - Wang, Yu Tai

AU - Yeh, Lin Chi

AU - Edwardo Rudon, Romel

AU - Lin, Kuan Wei

AU - Yang, Wei Jong

AU - Fann, Yang C.

AU - Chung, Pau Choo

PY - 2023

Y1 - 2023

N2 - Federated Learning (FL) provides an approach for performing the collaborative training of AI models without compromising data privacy. However, traditional implementations of FL require complex deployment strategies, making it challenging to perform training across multiple data centers. To address this issue, this article presents a platform designated as Federated Learning Agent (FLAg) which allows users to delegate their federated learning tasks to an automated process. FLAg features digital pathology databases as well as multiple pretrained models. The security of FLAg is ensured through its deployment on an HPC system and bastion host. While FLAg itself only offers FL training services, users may perform data annotation and inference through its integration with a proprietary ALOVAS AI pathology platform for a complete end-to-end process which includes annotation, FL training, and inference.

AB - Federated Learning (FL) provides an approach for performing the collaborative training of AI models without compromising data privacy. However, traditional implementations of FL require complex deployment strategies, making it challenging to perform training across multiple data centers. To address this issue, this article presents a platform designated as Federated Learning Agent (FLAg) which allows users to delegate their federated learning tasks to an automated process. FLAg features digital pathology databases as well as multiple pretrained models. The security of FLAg is ensured through its deployment on an HPC system and bastion host. While FLAg itself only offers FL training services, users may perform data annotation and inference through its integration with a proprietary ALOVAS AI pathology platform for a complete end-to-end process which includes annotation, FL training, and inference.

KW - Federated Learning

KW - High-performance computing

KW - Inference

KW - Pathology

KW - Segmentation

UR - https://www.scopus.com/pages/publications/85168666847

U2 - 10.1109/CAI54212.2023.00139

DO - 10.1109/CAI54212.2023.00139

M3 - 会议稿件

AN - SCOPUS:85168666847

T3 - Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023

SP - 314

EP - 315

BT - Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 5 June 2023 through 6 June 2023

ER -

Chiu YJ, Chuang CC, Wang YT, Yeh LC, Edwardo Rudon R, Lin KW et al. FLAg: An automated client-independent federated learning system on HPC for digital pathology slice training. In Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 314-315. (Proceedings - 2023 IEEE Conference on Artificial Intelligence, CAI 2023). doi: 10.1109/CAI54212.2023.00139

FLAg: An automated client-independent federated learning system on HPC for digital pathology slice training

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this