Matches in SemOpenAlex for { <https://semopenalex.org/work/W3182125009> ?p ?o ?g. }
- W3182125009 endingPage "24" @default.
- W3182125009 startingPage "1" @default.
- W3182125009 abstract "Federated learning (FL) is a distributed machine learning strategy that generates a global model by learning from multiple decentralized edge clients. FL enables on-device training, keeping the client’s local data private, and further, updating the global model based on the local model updates. While FL methods offer several advantages, including scalability and data privacy, they assume there are available computational resources at each edge-device/client. However, the Internet-of-Things (IoT)-enabled devices, e.g., robots, drone swarms, and low-cost computing devices (e.g., Raspberry Pi), may have limited processing ability, low bandwidth and power, or limited storage capacity. In this survey article, we propose to answer this question: how to train distributed machine learning models for resource-constrained IoT devices? To this end, we first explore the existing studies on FL, relative assumptions for distributed implementation using IoT devices, and explore their drawbacks. We then discuss the implementation challenges and issues when applying FL to an IoT environment. We highlight an overview of FL and provide a comprehensive survey of the problem statements and emerging challenges, particularly during applying FL within heterogeneous IoT environments. Finally, we point out the future research directions for scientists and researchers who are interested in working at the intersection of FL and resource-constrained IoT environments." @default.
- W3182125009 created "2021-07-19" @default.
- W3182125009 creator A5032642808 @default.
- W3182125009 creator A5052883326 @default.
- W3182125009 creator A5077711449 @default.
- W3182125009 creator A5078335465 @default.
- W3182125009 creator A5090396089 @default.
- W3182125009 date "2022-01-01" @default.
- W3182125009 modified "2023-10-09" @default.
- W3182125009 title "A Survey on Federated Learning for Resource-Constrained IoT Devices" @default.
- W3182125009 cites W1559136758 @default.
- W3182125009 cites W1968265138 @default.
- W3182125009 cites W1971991172 @default.
- W3182125009 cites W2051267297 @default.
- W3182125009 cites W2056899845 @default.
- W3182125009 cites W2083026317 @default.
- W3182125009 cites W2087811006 @default.
- W3182125009 cites W2104208424 @default.
- W3182125009 cites W2143104527 @default.
- W3182125009 cites W2145680191 @default.
- W3182125009 cites W2161229593 @default.
- W3182125009 cites W2165698076 @default.
- W3182125009 cites W2199097987 @default.
- W3182125009 cites W2289252105 @default.
- W3182125009 cites W2515287984 @default.
- W3182125009 cites W2518511512 @default.
- W3182125009 cites W2603810864 @default.
- W3182125009 cites W2613264175 @default.
- W3182125009 cites W2624989916 @default.
- W3182125009 cites W2751904527 @default.
- W3182125009 cites W2767079719 @default.
- W3182125009 cites W2786070938 @default.
- W3182125009 cites W2794624686 @default.
- W3182125009 cites W2808420356 @default.
- W3182125009 cites W2885981521 @default.
- W3182125009 cites W2896422817 @default.
- W3182125009 cites W2911450448 @default.
- W3182125009 cites W2912213068 @default.
- W3182125009 cites W2913340405 @default.
- W3182125009 cites W2920095265 @default.
- W3182125009 cites W2930926105 @default.
- W3182125009 cites W2949896761 @default.
- W3182125009 cites W2950865323 @default.
- W3182125009 cites W2951483008 @default.
- W3182125009 cites W2951832089 @default.
- W3182125009 cites W2954070046 @default.
- W3182125009 cites W2962804345 @default.
- W3182125009 cites W2963106566 @default.
- W3182125009 cites W2963318081 @default.
- W3182125009 cites W2963456518 @default.
- W3182125009 cites W2964162474 @default.
- W3182125009 cites W2969460181 @default.
- W3182125009 cites W2970606380 @default.
- W3182125009 cites W2972882814 @default.
- W3182125009 cites W2974175488 @default.
- W3182125009 cites W2974429275 @default.
- W3182125009 cites W2975802305 @default.
- W3182125009 cites W2977797911 @default.
- W3182125009 cites W2979637109 @default.
- W3182125009 cites W2979754840 @default.
- W3182125009 cites W2980713544 @default.
- W3182125009 cites W2982011653 @default.
- W3182125009 cites W2989289980 @default.
- W3182125009 cites W2990700079 @default.
- W3182125009 cites W2998045710 @default.
- W3182125009 cites W2999074226 @default.
- W3182125009 cites W3001299093 @default.
- W3182125009 cites W3001989995 @default.
- W3182125009 cites W3005429940 @default.
- W3182125009 cites W3006403184 @default.
- W3182125009 cites W3006655855 @default.
- W3182125009 cites W3009627224 @default.
- W3182125009 cites W3009927559 @default.
- W3182125009 cites W3015636663 @default.
- W3182125009 cites W3016378036 @default.
- W3182125009 cites W3016560828 @default.
- W3182125009 cites W3016632787 @default.
- W3182125009 cites W3018040655 @default.
- W3182125009 cites W3024699729 @default.
- W3182125009 cites W3029897895 @default.
- W3182125009 cites W3035572636 @default.
- W3182125009 cites W3044274646 @default.
- W3182125009 cites W3048448986 @default.
- W3182125009 cites W3051272477 @default.
- W3182125009 cites W3081130510 @default.
- W3182125009 cites W3084128899 @default.
- W3182125009 cites W3091476023 @default.
- W3182125009 cites W3095611529 @default.
- W3182125009 cites W3096109293 @default.
- W3182125009 cites W3097185144 @default.
- W3182125009 cites W3103802018 @default.
- W3182125009 cites W3105122387 @default.
- W3182125009 cites W3105324058 @default.
- W3182125009 cites W3106378891 @default.
- W3182125009 cites W3106445841 @default.
- W3182125009 cites W3109723249 @default.
- W3182125009 cites W3127743396 @default.
- W3182125009 cites W3129329365 @default.