지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- Korean Institute of Information Scientists and Engineers Journal of Computing Science and Engineering Journal of Computing Science and Engineering Vol.16 No.1
- 발행연도
- 2022.3
- 수록면
- 52 - 62 (11page)
- DOI
- 10.5626/JCSE.2022.16.1.52
이용수
초록· 키워드
오류제보하기
Federated learning (FL) is a new machine learning paradigm, where multiple clients learn their local models to collaboratively integrate into a single global model. Unlike centralized learning, the global model being integrated cannot be tested in FL as the server does not collect any data samples; further, the global model is often sent back and immediately applied to clients even in the middle of training such as Gboard. Therefore, if the performance of the global model is not stable, which is, unfortunately, the case in many FL scenarios with non-IID data, clients can be provided with an inaccurate model. This paper explores the main reason for this training instability of FL, that is, what we call temporary imbalance that happens across rounds, leading to loss of knowledge from previous rounds. To solve this problem, we propose a dataset condensation method to summarize the local data for each client without compromising on privacy. The condensed data are transmitted to the server with the local model and utilized by the server to ensure stable and consistent performance of the global model. Experimental results show that the global model not only achieves training stability but also exhibits a fast convergence speed.
목차
Abstract
I. INTRODUCTION
II. RELATED WORK
III. ANALYSIS ON TRAINING INSTABILITY OF FEDERATED LEARNING
IV. METHOD
V. EXPERIEMENTS
VI. CONCLUSION
REFERENCES
참고문헌 (27)
참고문헌 신청
B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. Y. Arcas, ‘‘Communication-efficient learning of deep networks from decentralized data,’’ in Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, 2017, pp. 1273–1282.
M. Aledhari, R. Razzak, R. M. Parizi and F. Saeed, "Federated learning: a survey on enabling technologies, protocols, and applications," IEEE Access, vol. 8, pp. 140699-140725, 2020.
J. Wang, Z. Charles, Z. Xu, G. Joshi, H.B. McMahan, M. Al-Shedivat, et al., “A field guide to federated optimization,” 2017 [Online]. Available: https://arxiv.org/abs/2107.06917.
A. Hard, K. Rao, R. Mathews, S. Ramaswamy, F. Beaufays, S. Augenstein, H. Eichner, C. Kiddon, and D. Ramage, “Federated learning for mobile keyboard prediction,” 2018 [Online]. Available: https://arxiv.org/abs/1811.03604.
W. Li, F. Milletari, D. Xu, N. Rieke, J. Hancox, W., Zhu, et al., “Privacy-preserving federated brain tumour segmentation,” 2019 [Online]. Available: https://arxiv.org/abs/1910.00962.
M. Aledhari, R. Razzak, R. M. Parizi and F. Saeed, "Federated learning: a survey on enabling technologies, protocols, and applications," IEEE Access, vol. 8, pp. 140699-140725, 2020.
J. Wang, Z. Charles, Z. Xu, G. Joshi, H.B. McMahan, M. Al-Shedivat, et al., “A field guide to federated optimization,” 2017 [Online]. Available: https://arxiv.org/abs/2107.06917.
A. Hard, K. Rao, R. Mathews, S. Ramaswamy, F. Beaufays, S. Augenstein, H. Eichner, C. Kiddon, and D. Ramage, “Federated learning for mobile keyboard prediction,” 2018 [Online]. Available: https://arxiv.org/abs/1811.03604.
W. Li, F. Milletari, D. Xu, N. Rieke, J. Hancox, W., Zhu, et al., “Privacy-preserving federated brain tumour segmentation,” 2019 [Online]. Available: https://arxiv.org/abs/1910.00962.
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
연합학습에서 공정한 훈련을 위한 클라이언트 훈련 규모 조율 방법
Proceedings of KIIT Conference
2023 .11
-
Adaptive Client Sampling and Feature Separation: Towards Efficient Personalization in Non-IID Federated Learning
Journal of information and communication convergence engineering
2025 .03
-
Image-to-Text approach with Large Language Model for Client Selection in Federated Learning
대한산업공학회 추계학술대회 논문집
2023 .11
-
연합학습에서의 양자화 레벨에 따른 영향 분석
대한전자공학회 학술대회
2021 .06
-
연합 학습 모델에서 비정상 클라이언트 클러스터링
대한전자공학회 학술대회
2022 .06
-
사용자별 가중치 표준 편차를 활용한 Federated Learning 성능 향상 기법
한국통신학회 학술대회논문집
2021 .06
-
연합 학습을 위한 로우 랭크 분해 모델
대한전자공학회 학술대회
2021 .06
-
연합학습(Federated Learning) 네트워크에서의 형평성 보장 기법에 관한 연구
한국통신학회논문지
2023 .06
-
A Review of Secure Healthcare Data Analytics using Federated Machine Learning and Blockchain Technology
IEIE Transactions on Smart Processing & Computing
2024 .06
-
연합학습에서의 백도어 공격에 대한 방어 기법 연구
대한전자공학회 학술대회
2022 .06
-
안전한 HVA를 위한 클라이언트 BBS 시스템의 설계
한국컴퓨터정보학회논문지
2018 .09
-
Towards Accuracy-Aware Client Selection in Federated Learning
한국통신학회 학술대회논문집
2022 .11
-
Flower 을 사용한 점진적 연합학습시스템 구성
JOURNAL OF PLATFORM TECHNOLOGY
2023 .08
-
기반모델(Foundation Model)과 연합학습(Federated Learning)의 동향
한국통신학회 학술대회논문집
2024 .11
-
Federated Self-Supervised Learning in Sensor-Based Human Activity Recognition with Hybrid Approach
대한산업공학회 추계학술대회 논문집
2024 .10
-
Design of Client-Server Model For Effective Processing and Utilization of Bigdata
한국지능정보시스템학회 학술대회논문집
2016 .11
-
연합학습 시 글로벌 모델 성능 향상을 위한 기여도 기반 집계 알고리즘
한국정보기술학회논문지
2023 .12
-
Federated Learning with Learned Sufficient Statistic and Generative Models
대한산업공학회 춘계공동학술대회 논문집
2021 .06
-
Personalized Progressive Federated Learning with Leveraging Client-Specific Vertical Features: Model Development and Validation
한국지능정보시스템학회 학술대회논문집
2022 .11
-
교차소거법을 이용한 Non-IID 환경에서의 연합학습 프레임워크 설계
한국지능시스템학회 논문지
2021 .08
이 논문의 저자 정보
이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0