Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036723732> ?p ?o ?g. }
- W3036723732 abstract "We study federated learning (FL), which enables mobile devices to utilize their local datasets to collaboratively train a global model with the help of a central server, while keeping data localized. At each iteration, the server broadcasts the current global model to the devices for local training, and aggregates the local model updates from the devices to update the global model. Previous work on the communication efficiency of FL has mainly focused on the aggregation of model updates from the devices, assuming perfect broadcasting of the global model. In this paper, we instead consider broadcasting a compressed version of the global model. This is to further reduce the communication cost of FL, which can be particularly limited when the global model is to be transmitted over a wireless medium. We introduce a lossy FL (LFL) algorithm, in which both the global model and the local model updates are quantized before being transmitted. We analyze the convergence behavior of the proposed LFL algorithm assuming the availability of accurate local model updates at the server. Numerical experiments show that the proposed LFL scheme, which quantizes the global model update (with respect to the global model estimate at the devices) rather than the global model itself, significantly outperforms other existing schemes studying quantization of the global model at the PS-to-device direction. Also, the performance loss of the proposed scheme is marginal compared to the fully lossless approach, where the PS and the devices transmit their messages entirely without any quantization." @default.
- W3036723732 created "2020-06-25" @default.
- W3036723732 creator A5010987707 @default.
- W3036723732 creator A5016883501 @default.
- W3036723732 creator A5042307561 @default.
- W3036723732 creator A5053530986 @default.
- W3036723732 date "2021-05-04" @default.
- W3036723732 modified "2023-10-16" @default.
- W3036723732 title "Federated Learning With Quantized Global Model Updates" @default.
- W3036723732 cites W1522301498 @default.
- W3036723732 cites W2116612304 @default.
- W3036723732 cites W2138243089 @default.
- W3036723732 cites W2435473771 @default.
- W3036723732 cites W2535838896 @default.
- W3036723732 cites W2541884796 @default.
- W3036723732 cites W2552857149 @default.
- W3036723732 cites W2774000609 @default.
- W3036723732 cites W2807006176 @default.
- W3036723732 cites W2891970177 @default.
- W3036723732 cites W2892209803 @default.
- W3036723732 cites W2900182564 @default.
- W3036723732 cites W2905444686 @default.
- W3036723732 cites W2907379776 @default.
- W3036723732 cites W2941142392 @default.
- W3036723732 cites W2946815927 @default.
- W3036723732 cites W2950539955 @default.
- W3036723732 cites W2951781666 @default.
- W3036723732 cites W2954365017 @default.
- W3036723732 cites W2963179579 @default.
- W3036723732 cites W2963318081 @default.
- W3036723732 cites W2963766684 @default.
- W3036723732 cites W2972497108 @default.
- W3036723732 cites W2975156709 @default.
- W3036723732 cites W2978110818 @default.
- W3036723732 cites W2978422189 @default.
- W3036723732 cites W2982654255 @default.
- W3036723732 cites W2982655620 @default.
- W3036723732 cites W2994779554 @default.
- W3036723732 cites W2995022099 @default.
- W3036723732 cites W2995653155 @default.
- W3036723732 cites W2999477684 @default.
- W3036723732 cites W3004384679 @default.
- W3036723732 cites W3005503558 @default.
- W3036723732 cites W3021221399 @default.
- W3036723732 cites W3034666238 @default.
- W3036723732 cites W3034741284 @default.
- W3036723732 cites W3037209298 @default.
- W3036723732 cites W3038022836 @default.
- W3036723732 cites W3047475040 @default.
- W3036723732 cites W3102816259 @default.
- W3036723732 cites W3105122387 @default.
- W3036723732 cites W3118608800 @default.
- W3036723732 cites W3212066104 @default.
- W3036723732 hasPublicationYear "2021" @default.
- W3036723732 type Work @default.
- W3036723732 sameAs 3036723732 @default.
- W3036723732 citedByCount "20" @default.
- W3036723732 countsByYear W30367237322020 @default.
- W3036723732 countsByYear W30367237322021 @default.
- W3036723732 crossrefType "journal-article" @default.
- W3036723732 hasAuthorship W3036723732A5010987707 @default.
- W3036723732 hasAuthorship W3036723732A5016883501 @default.
- W3036723732 hasAuthorship W3036723732A5042307561 @default.
- W3036723732 hasAuthorship W3036723732A5053530986 @default.
- W3036723732 hasConcept C110157686 @default.
- W3036723732 hasConcept C11413529 @default.
- W3036723732 hasConcept C120314980 @default.
- W3036723732 hasConcept C134306372 @default.
- W3036723732 hasConcept C154945302 @default.
- W3036723732 hasConcept C15744967 @default.
- W3036723732 hasConcept C162324750 @default.
- W3036723732 hasConcept C165021410 @default.
- W3036723732 hasConcept C19417346 @default.
- W3036723732 hasConcept C2777303404 @default.
- W3036723732 hasConcept C2779582901 @default.
- W3036723732 hasConcept C28855332 @default.
- W3036723732 hasConcept C31258907 @default.
- W3036723732 hasConcept C33923547 @default.
- W3036723732 hasConcept C41008148 @default.
- W3036723732 hasConcept C50522688 @default.
- W3036723732 hasConcept C77618280 @default.
- W3036723732 hasConcept C78548338 @default.
- W3036723732 hasConcept C81081738 @default.
- W3036723732 hasConceptScore W3036723732C110157686 @default.
- W3036723732 hasConceptScore W3036723732C11413529 @default.
- W3036723732 hasConceptScore W3036723732C120314980 @default.
- W3036723732 hasConceptScore W3036723732C134306372 @default.
- W3036723732 hasConceptScore W3036723732C154945302 @default.
- W3036723732 hasConceptScore W3036723732C15744967 @default.
- W3036723732 hasConceptScore W3036723732C162324750 @default.
- W3036723732 hasConceptScore W3036723732C165021410 @default.
- W3036723732 hasConceptScore W3036723732C19417346 @default.
- W3036723732 hasConceptScore W3036723732C2777303404 @default.
- W3036723732 hasConceptScore W3036723732C2779582901 @default.
- W3036723732 hasConceptScore W3036723732C28855332 @default.
- W3036723732 hasConceptScore W3036723732C31258907 @default.
- W3036723732 hasConceptScore W3036723732C33923547 @default.
- W3036723732 hasConceptScore W3036723732C41008148 @default.
- W3036723732 hasConceptScore W3036723732C50522688 @default.
- W3036723732 hasConceptScore W3036723732C77618280 @default.