Skip to content

Latest commit

 

History

History
83 lines (55 loc) · 6.49 KB

File metadata and controls

83 lines (55 loc) · 6.49 KB

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


List

부산대
부경대
서울대
KETI
ETC


부산대

기조연설 주제: 웹 3.0, 블록체인과 미래사회 전망(부산대 김호원 교수)

부경대

[Sandi Rahmadika@부경대]

Practical Concerns in Enforcing Ethereum Smart Contracts as a Rewarding Platform in Decentralized Learning, 연합학습의 인센티브 플랫폼으로써 이더리움 스마트 컨트랙트를 시행하는 경우의 실무적 고려사항, https://www.koreascience.or.kr/article/JAKO202006957583461.page

Privacy-Preserving Cross-Silo Federated Learning with a Cryptocurrency in Edge Networks, 에지 네트워크 상에서 암호화폐를 이용한 프라이버시보호 크로스사일로 연합학습, https://repository.pknu.ac.kr:8443/handle/2021.oak/1123 Unlinkable Collaborative Learning Transactions: Privacy-Awareness in Decentralized Approaches, https://ieeexplore.ieee.org/abstract/document/9417207

Blockchain technology for providing an architecture model of decentralized personal health information, https://journals.sagepub.com/doi/full/10.1177/1847979018790589 PDPM: A Patient-Defined Data Privacy Management with Nudge Theory in Decentralized E-Health Environments, https://www.jstage.jst.go.jp/article/transinf/E104.D/11/E104.D_2021NGP0015/_pdf

A Study on Blockchain-Based Asynchronous Federated Learning Framework, https://papersearch.net/google_link/fulltext.asp?file_name=52825060.pdf

서울대

문수묵 교수, https://altair.snu.ac.kr/

박상현, https://sharp-saw-d58.notion.site/Luke-Park-d4edb5bf446b479796d0d9bfe422d92a

열악한 환경에서도 효과적인 블록체인 기반의 탈중앙화 연합학습 플랫폼, https://www.dbpia.co.kr/Journal/articleDetail?nodeId=NODE09874860

본 연구에서는 불균일한 데이터 분포 환경을 다룰 수 있도록 블록체인 기반의 탈중앙화 연합학습 플랫폼을 제안함으로써 다음 두 목표를 이루고자 한다. 첫째, 각 노드가 가지고 있는 데이터들이 불균일하고 심지어 거짓된 데이터가 섞여 있어도 글로벌 모델의 수렴성을 유지한다. 둘째, 비슷한 분포의 데이터를 가지고 있는 노드들이 자신들의 데이터에 적합한 독자적인 글로벌 모델을 가진다.

KETI

KETI (한국전자기술연구원, 구 전자부품연구원)
Design and Development of Server-Client Cooperation Framework for Federated Learning, https://ieeexplore.ieee.org/document/9829693

Federated learning is a machine learning technique that enables distributed training without explicitly data sharing between multiple heterogeneous devices. In this paper, we propose and develop a practical federated learning framework to effectively support model deployment, aggregation, and client device monitoring. The proposed approach is designed as a microarchitecture service using container-related technologies such as _Docker, Kubernetes_, and Prometheus.

ETC

[연세대] Blockchained On-Device Federated Learning - arXiv, https://arxiv.org/abs/1808.03949

[아주대] AMBLE: Adjusting mini-batch and local epoch for federated learning with heterogeneous devices, https://www.sciencedirect.com/science/article/abs/pii/S0743731522001757

[박준범⋅박종서† 한국항공대학교 컴퓨터 공학과] 블록체인 기반의 연합학습 구현, https://scienceon.kisti.re.kr/srch/selectPORSrchArticle.do?추=JAKO202032362242331&윳=NART

[공주대] Efficient privacy-preserving machine learning for blockchain network, https://ieeexplore.ieee.org/abstract/document/8827509


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