FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378976270> ?p ?o ?g. }

• W4378976270 endingPage "54209" @default.
• W4378976270 startingPage "54188" @default.
• W4378976270 abstract "Recent developments in deep learning have contributed to numerous success stories in healthcare. The performance of a deep learning model generally improves with the size of the training data. However, there are privacy, ownership, and regulatory issues that prevent combining medical data into traditional centralized storage. Decentralized learning approaches enable collaborative model training by distributing the learning process among several nodes or devices. Conceptually, decentralized learning builds on earlier work in distributed optimization, but the focus of this paper is on recent and emerging techniques such as Federated Learning (FL), Split Learning (SL), and hybrid Split-Federated Learning (SFL). With common, universal deep learning models and centralized aggregator servers, FL overcomes the difficulties of centralized training. Additionally, patient data remains at the local party, upholding the security and anonymity of the data. SL enables machine learning without directly accessing data on clients or end devices. It further enhances privacy in a decentralized setting and mitigates clients’ storage issues. In this survey, we first provide a contemporary survey of FL, SL, and SFL approaches. Second, we discuss their state-of-the-art applications in healthcare, particularly in medical image analysis. Third, we review these emerging decentralized learning approaches under challenging conditions such as statistical and system heterogeneity, privacy preservation, communication efficiency, fairness, etc. Then, we address existing approaches to tackle these challenges. We detail unique complications related to healthcare applications including data, privacy and security, and communication challenges. Finally, we outline potential areas for further research on emerging decentralized learning techniques in healthcare, including developing personalized models, reducing bias, incorporating hybrid non-IID features, hyperparameter tuning, developing sufficient incentive mechanisms, and incorporating domain expertise knowledge." @default.
• W4378976270 created "2023-06-02" @default.
• W4378976270 creator A5011637244 @default.
• W4378976270 creator A5012187461 @default.
• W4378976270 creator A5073725553 @default.
• W4378976270 date "2023-01-01" @default.
• W4378976270 modified "2023-10-15" @default.
• W4378976270 title "Decentralized Learning in Healthcare: A Review of Emerging Techniques" @default.
• W4378976270 cites W1595357546 @default.
• W4378976270 cites W1641498739 @default.
• W4378976270 cites W1969496006 @default.
• W4378976270 cites W2007339694 @default.
• W4378976270 cites W2041616772 @default.
• W4378976270 cites W2068143382 @default.
• W4378976270 cites W2106033751 @default.
• W4378976270 cites W2117539524 @default.
• W4378976270 cites W2167868121 @default.
• W4378976270 cites W2473418344 @default.
• W4378976270 cites W2560584411 @default.
• W4378976270 cites W2604830170 @default.
• W4378976270 cites W2606065148 @default.
• W4378976270 cites W2623808523 @default.
• W4378976270 cites W2744692634 @default.
• W4378976270 cites W2765961644 @default.
• W4378976270 cites W2777186991 @default.
• W4378976270 cites W2783522756 @default.
• W4378976270 cites W2791338647 @default.
• W4378976270 cites W2797527544 @default.
• W4378976270 cites W2828862258 @default.
• W4378976270 cites W2897230576 @default.
• W4378976270 cites W2912213068 @default.
• W4378976270 cites W2917418342 @default.
• W4378976270 cites W2963183964 @default.
• W4378976270 cites W2963209930 @default.
• W4378976270 cites W2963466845 @default.
• W4378976270 cites W2970885630 @default.
• W4378976270 cites W2977072935 @default.
• W4378976270 cites W2979637109 @default.
• W4378976270 cites W2989289980 @default.
• W4378976270 cites W2991372685 @default.
• W4378976270 cites W2996582092 @default.
• W4378976270 cites W2997545378 @default.
• W4378976270 cites W2998045710 @default.
• W4378976270 cites W3009048827 @default.
• W4378976270 cites W3011726479 @default.
• W4378976270 cites W3015636663 @default.
• W4378976270 cites W3018102029 @default.
• W4378976270 cites W3018464563 @default.
• W4378976270 cites W3027572331 @default.
• W4378976270 cites W3040685212 @default.
• W4378976270 cites W3081500256 @default.
• W4378976270 cites W3081630787 @default.
• W4378976270 cites W3086590218 @default.
• W4378976270 cites W3088405625 @default.
• W4378976270 cites W3089184847 @default.
• W4378976270 cites W3089578458 @default.
• W4378976270 cites W3091851474 @default.
• W4378976270 cites W3091884625 @default.
• W4378976270 cites W3098488418 @default.
• W4378976270 cites W3099084711 @default.
• W4378976270 cites W3100506742 @default.
• W4378976270 cites W3100779497 @default.
• W4378976270 cites W3101156210 @default.
• W4378976270 cites W3103802018 @default.
• W4378976270 cites W3109503640 @default.
• W4378976270 cites W3123411108 @default.
• W4378976270 cites W3126842209 @default.
• W4378976270 cites W3134285077 @default.
• W4378976270 cites W3135345339 @default.
• W4378976270 cites W3138795569 @default.
• W4378976270 cites W3150684546 @default.
• W4378976270 cites W3157242219 @default.
• W4378976270 cites W3159623990 @default.
• W4378976270 cites W3160882100 @default.
• W4378976270 cites W3167262308 @default.
• W4378976270 cites W3172681723 @default.
• W4378976270 cites W3173670432 @default.
• W4378976270 cites W3180884825 @default.
• W4378976270 cites W3182336762 @default.
• W4378976270 cites W3193066552 @default.
• W4378976270 cites W3195545894 @default.
• W4378976270 cites W3198751165 @default.
• W4378976270 cites W3201745428 @default.
• W4378976270 cites W3204212595 @default.
• W4378976270 cites W3206468898 @default.
• W4378976270 cites W3207166205 @default.
• W4378976270 cites W3210668366 @default.
• W4378976270 cites W3213008925 @default.
• W4378976270 cites W3215126987 @default.
• W4378976270 cites W4206279885 @default.
• W4378976270 cites W4210326097 @default.
• W4378976270 cites W4210683768 @default.
• W4378976270 cites W4212881588 @default.
• W4378976270 cites W4220993128 @default.
• W4378976270 cites W4224311344 @default.
• W4378976270 cites W4225317590 @default.
• W4378976270 cites W4225926344 @default.
• W4378976270 cites W4232478844 @default.

• next