Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205487680> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4205487680 abstract "Advancements in mobile technology led to the manufacturing of smart devices that have started generating massive amounts of data. This triggered a new interest in developing intelligent applications that can harness this data's power and provide meaningful insights from it. This data from various devices needs to be aggregated at a central location to provide more accurate predictions, raising severe bandwidth, privacy, and latency issues. This paper presents a novel distributed learning approach that trains a Variational Auto Encoder at each client and then uses this model's generative capabilities to create a sample set of points on the server. The server aggregates these samples from all the clients and then trains a single global model whose parameters are communicated back to the clients. We show through our results that the amount of data transmitted between clients and the server is significantly lower when compared to the federated learning as well as a central learning approach. We also show that our approach outperforms the federated learning approach in terms of accuracy by more than 3% when the data is distributed in a non-iid fashion and at the same time sees a small drop in accuracy which less than 2% in an iid scenario when compared to federated learning and central learning methods. We have also shown how the amount data transmitted and the variation in accuracies when the number of clients vary between 2, 5 and 10." @default.
- W4205487680 created "2022-01-26" @default.
- W4205487680 creator A5060979479 @default.
- W4205487680 creator A5063245652 @default.
- W4205487680 creator A5081392781 @default.
- W4205487680 date "2022-01-04" @default.
- W4205487680 modified "2023-09-28" @default.
- W4205487680 title "Communication Efficient Distributed Learning Using Variational Auto Encoders" @default.
- W4205487680 doi "https://doi.org/10.1109/comsnets53615.2022.9668564" @default.
- W4205487680 hasPublicationYear "2022" @default.
- W4205487680 type Work @default.
- W4205487680 citedByCount "0" @default.
- W4205487680 crossrefType "proceedings-article" @default.
- W4205487680 hasAuthorship W4205487680A5060979479 @default.
- W4205487680 hasAuthorship W4205487680A5063245652 @default.
- W4205487680 hasAuthorship W4205487680A5081392781 @default.
- W4205487680 hasConcept C101738243 @default.
- W4205487680 hasConcept C108583219 @default.
- W4205487680 hasConcept C111919701 @default.
- W4205487680 hasConcept C118505674 @default.
- W4205487680 hasConcept C119857082 @default.
- W4205487680 hasConcept C120314980 @default.
- W4205487680 hasConcept C154945302 @default.
- W4205487680 hasConcept C15744967 @default.
- W4205487680 hasConcept C167966045 @default.
- W4205487680 hasConcept C186967261 @default.
- W4205487680 hasConcept C190839683 @default.
- W4205487680 hasConcept C19417346 @default.
- W4205487680 hasConcept C205649164 @default.
- W4205487680 hasConcept C2776257435 @default.
- W4205487680 hasConcept C2779582901 @default.
- W4205487680 hasConcept C2992525071 @default.
- W4205487680 hasConcept C31258907 @default.
- W4205487680 hasConcept C39890363 @default.
- W4205487680 hasConcept C41008148 @default.
- W4205487680 hasConcept C58640448 @default.
- W4205487680 hasConcept C76155785 @default.
- W4205487680 hasConcept C79403827 @default.
- W4205487680 hasConcept C82876162 @default.
- W4205487680 hasConcept C93996380 @default.
- W4205487680 hasConceptScore W4205487680C101738243 @default.
- W4205487680 hasConceptScore W4205487680C108583219 @default.
- W4205487680 hasConceptScore W4205487680C111919701 @default.
- W4205487680 hasConceptScore W4205487680C118505674 @default.
- W4205487680 hasConceptScore W4205487680C119857082 @default.
- W4205487680 hasConceptScore W4205487680C120314980 @default.
- W4205487680 hasConceptScore W4205487680C154945302 @default.
- W4205487680 hasConceptScore W4205487680C15744967 @default.
- W4205487680 hasConceptScore W4205487680C167966045 @default.
- W4205487680 hasConceptScore W4205487680C186967261 @default.
- W4205487680 hasConceptScore W4205487680C190839683 @default.
- W4205487680 hasConceptScore W4205487680C19417346 @default.
- W4205487680 hasConceptScore W4205487680C205649164 @default.
- W4205487680 hasConceptScore W4205487680C2776257435 @default.
- W4205487680 hasConceptScore W4205487680C2779582901 @default.
- W4205487680 hasConceptScore W4205487680C2992525071 @default.
- W4205487680 hasConceptScore W4205487680C31258907 @default.
- W4205487680 hasConceptScore W4205487680C39890363 @default.
- W4205487680 hasConceptScore W4205487680C41008148 @default.
- W4205487680 hasConceptScore W4205487680C58640448 @default.
- W4205487680 hasConceptScore W4205487680C76155785 @default.
- W4205487680 hasConceptScore W4205487680C79403827 @default.
- W4205487680 hasConceptScore W4205487680C82876162 @default.
- W4205487680 hasConceptScore W4205487680C93996380 @default.
- W4205487680 hasLocation W42054876801 @default.
- W4205487680 hasOpenAccess W4205487680 @default.
- W4205487680 hasPrimaryLocation W42054876801 @default.
- W4205487680 hasRelatedWork W2624872001 @default.
- W4205487680 hasRelatedWork W2903766720 @default.
- W4205487680 hasRelatedWork W3080181681 @default.
- W4205487680 hasRelatedWork W3125572383 @default.
- W4205487680 hasRelatedWork W3131867864 @default.
- W4205487680 hasRelatedWork W4205487680 @default.
- W4205487680 hasRelatedWork W4287331763 @default.
- W4205487680 hasRelatedWork W4287996110 @default.
- W4205487680 hasRelatedWork W4312788555 @default.
- W4205487680 hasRelatedWork W4319775894 @default.
- W4205487680 isParatext "false" @default.
- W4205487680 isRetracted "false" @default.
- W4205487680 workType "article" @default.