FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213862827> ?p ?o ?g. }

• W3213862827 endingPage "1175" @default.
• W3213862827 startingPage "1165" @default.
• W3213862827 abstract "Federated learning (FL) is a promising paradigm to empower on-device intelligence in Industrial Internet of Things (IIoT) due to its capability of training machine learning models across multiple IIoT devices while preserving the privacy of their local data. However, the distributed architecture of FL relies on aggregating the parameter list from the remote devices, which poses potential security risks caused by malicious devices. In this article, we propose a flexible and robust aggregation rule, called auto-weighted geometric median ( <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>AutoGM</monospace> ), and analyze the robustness against outliers in the inputs. To obtain the value of <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>AutoGM</monospace> , we design an algorithm based on the alternating optimization strategy. Using <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>AutoGM</monospace> as aggregation rule, we propose two robust FL solutions <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>AutoGM_FL</monospace> and <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>AutoGM_PFL</monospace> . <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>AutoGM_FL</monospace> learns a shared global model using the standard FL paradigm, and <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>AutoGM_PFL</monospace> learns a personalized model for each device. We conduct extensive experiments on the FEMNIST and Bosch IIoT datasets. The experimental results show that our solutions are robust against both model poisoning and data poisoning attacks. In particular, our solutions sustain high performance even when 30% of the nodes perform model or 50% of the nodes perform data poisoning attacks." @default.
• W3213862827 created "2021-11-22" @default.
• W3213862827 creator A5006655070 @default.
• W3213862827 creator A5071943253 @default.
• W3213862827 creator A5077317339 @default.
• W3213862827 date "2023-02-01" @default.
• W3213862827 modified "2023-10-16" @default.
• W3213862827 title "Byzantine-Robust Aggregation in Federated Learning Empowered Industrial IoT" @default.
• W3213862827 cites W2042986815 @default.
• W3213862827 cites W2136179595 @default.
• W3213862827 cites W2139137304 @default.
• W3213862827 cites W2410099853 @default.
• W3213862827 cites W2614254310 @default.
• W3213862827 cites W2794159901 @default.
• W3213862827 cites W2977797911 @default.
• W3213862827 cites W3004155269 @default.
• W3213862827 cites W3010012151 @default.
• W3213862827 cites W3021026170 @default.
• W3213862827 cites W3033686777 @default.
• W3213862827 cites W3044626808 @default.
• W3213862827 cites W3049097602 @default.
• W3213862827 cites W3086579950 @default.
• W3213862827 cites W3090288569 @default.
• W3213862827 cites W3094736543 @default.
• W3213862827 cites W3099185017 @default.
• W3213862827 cites W3113308842 @default.
• W3213862827 cites W3125796803 @default.
• W3213862827 cites W3130133360 @default.
• W3213862827 cites W3130916947 @default.
• W3213862827 cites W3131785880 @default.
• W3213862827 cites W3134070916 @default.
• W3213862827 cites W3180000121 @default.
• W3213862827 cites W3192530604 @default.
• W3213862827 cites W3201530369 @default.
• W3213862827 doi "https://doi.org/10.1109/tii.2021.3128164" @default.
• W3213862827 hasPublicationYear "2023" @default.
• W3213862827 type Work @default.
• W3213862827 sameAs 3213862827 @default.
• W3213862827 citedByCount "4" @default.
• W3213862827 countsByYear W32138628272022 @default.
• W3213862827 countsByYear W32138628272023 @default.
• W3213862827 crossrefType "journal-article" @default.
• W3213862827 hasAuthorship W3213862827A5006655070 @default.
• W3213862827 hasAuthorship W3213862827A5071943253 @default.
• W3213862827 hasAuthorship W3213862827A5077317339 @default.
• W3213862827 hasBestOaLocation W32138628272 @default.
• W3213862827 hasConcept C104317684 @default.
• W3213862827 hasConcept C119857082 @default.
• W3213862827 hasConcept C154945302 @default.
• W3213862827 hasConcept C185592680 @default.
• W3213862827 hasConcept C23123220 @default.
• W3213862827 hasConcept C41008148 @default.
• W3213862827 hasConcept C55493867 @default.
• W3213862827 hasConcept C63479239 @default.
• W3213862827 hasConceptScore W3213862827C104317684 @default.
• W3213862827 hasConceptScore W3213862827C119857082 @default.
• W3213862827 hasConceptScore W3213862827C154945302 @default.
• W3213862827 hasConceptScore W3213862827C185592680 @default.
• W3213862827 hasConceptScore W3213862827C23123220 @default.
• W3213862827 hasConceptScore W3213862827C41008148 @default.
• W3213862827 hasConceptScore W3213862827C55493867 @default.
• W3213862827 hasConceptScore W3213862827C63479239 @default.
• W3213862827 hasIssue "2" @default.
• W3213862827 hasLocation W32138628271 @default.
• W3213862827 hasLocation W32138628272 @default.
• W3213862827 hasOpenAccess W3213862827 @default.
• W3213862827 hasPrimaryLocation W32138628271 @default.
• W3213862827 hasRelatedWork W2144190808 @default.
• W3213862827 hasRelatedWork W2357241418 @default.
• W3213862827 hasRelatedWork W2366644548 @default.
• W3213862827 hasRelatedWork W2376314740 @default.
• W3213862827 hasRelatedWork W2384888906 @default.
• W3213862827 hasRelatedWork W2584455473 @default.
• W3213862827 hasRelatedWork W2961085424 @default.
• W3213862827 hasRelatedWork W4286629047 @default.
• W3213862827 hasRelatedWork W4306674287 @default.
• W3213862827 hasRelatedWork W4224009465 @default.
• W3213862827 hasVolume "19" @default.
• W3213862827 isParatext "false" @default.
• W3213862827 isRetracted "false" @default.
• W3213862827 magId "3213862827" @default.
• W3213862827 workType "article" @default.