FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310461189> ?p ?o ?g. }

• W4310461189 endingPage "2031" @default.
• W4310461189 startingPage "2022" @default.
• W4310461189 abstract "Foreseeing the evolution of brain connectivity between anatomical regions from a baseline observation can propel early disease diagnosis and clinical decision making. Such task becomes challenging when learning from multiple decentralized datasets with missing timepoints (e.g., datasets collected from different hospitals with a varying sequence of acquisitions). Federated learning (FL) is an emerging paradigm that enables collaborative learning among multiple clients (i.e., hospitals) in a fully privacy-preserving fashion. However, to the best of our knowledge, there is no FL work that foresees the time-dependent brain connectivity evolution from a single timepoint –let alone learning from non-iid decentralized longitudinal datasets with <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>varying acquisition timepoints</i> . In this paper, we propose the first FL framework to significantly boost the predictive performance of local hospitals with missing acquisition timepoints while benefiting from other hospitals with available data at those timepoints without sharing data. Specifically, we introduce 4D-FED-GNN+, a novel longitudinal federated GNN framework that works in (i) a uni-mode, where it acts as a graph self-encoder if the next timepoint is locally missing or (ii) in a dual-mode, where it concurrently acts as a graph generator and a self-encoder if the local follow-up data is available. Further, we propose a dual federation strategy, where (i) GNN layer-wise weight aggregation and (ii) pairwise GNN weight exchange between hospitals in a random order. To improve the performance of the poorly-conditioned hospitals (e.g., consecutive missing timepoints, intermediate missing timepoint), we further propose a second variant, namely 4D-FED-GNN++, which federates based on an ordering of the local hospitals computed using their incomplete sequential patterns. Our comprehensive experiments on real longitudinal datasets show that overall 4D-FED-GNN+ and 4D-FED-GNN++ significantly outperform benchmark methods. Our source code is available at https: //github.com/basiralab/4D-FedGNN-Plus." @default.
• W4310461189 created "2022-12-10" @default.
• W4310461189 creator A5015390160 @default.
• W4310461189 creator A5048784346 @default.
• W4310461189 date "2023-07-01" @default.
• W4310461189 modified "2023-10-13" @default.
• W4310461189 title "Federated Brain Graph Evolution Prediction using Decentralized Connectivity Datasets with Temporally-varying Acquisitions" @default.
• W4310461189 cites W1983485726 @default.
• W4310461189 cites W2101135654 @default.
• W4310461189 cites W2159929956 @default.
• W4310461189 cites W2606202972 @default.
• W4310461189 cites W2794107469 @default.
• W4310461189 cites W2809455333 @default.
• W4310461189 cites W2889302076 @default.
• W4310461189 cites W2898535604 @default.
• W4310461189 cites W2926315443 @default.
• W4310461189 cites W2942086449 @default.
• W4310461189 cites W2945589020 @default.
• W4310461189 cites W2954450472 @default.
• W4310461189 cites W2979428628 @default.
• W4310461189 cites W3038901217 @default.
• W4310461189 cites W3089578458 @default.
• W4310461189 cites W3090326428 @default.
• W4310461189 cites W3093170630 @default.
• W4310461189 cites W3094949157 @default.
• W4310461189 cites W3094958958 @default.
• W4310461189 cites W3095656329 @default.
• W4310461189 cites W3123459983 @default.
• W4310461189 cites W3126230197 @default.
• W4310461189 cites W3161501971 @default.
• W4310461189 cites W3192953632 @default.
• W4310461189 cites W3199459191 @default.
• W4310461189 cites W3206087786 @default.
• W4310461189 cites W3206207913 @default.
• W4310461189 cites W4241074797 @default.
• W4310461189 doi "https://doi.org/10.1109/tmi.2022.3225083" @default.
• W4310461189 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36441899" @default.
• W4310461189 hasPublicationYear "2023" @default.
• W4310461189 type Work @default.
• W4310461189 citedByCount "2" @default.
• W4310461189 crossrefType "journal-article" @default.
• W4310461189 hasAuthorship W4310461189A5015390160 @default.
• W4310461189 hasAuthorship W4310461189A5048784346 @default.
• W4310461189 hasConcept C108583219 @default.
• W4310461189 hasConcept C111919701 @default.
• W4310461189 hasConcept C118505674 @default.
• W4310461189 hasConcept C119857082 @default.
• W4310461189 hasConcept C124101348 @default.
• W4310461189 hasConcept C124952713 @default.
• W4310461189 hasConcept C132525143 @default.
• W4310461189 hasConcept C142362112 @default.
• W4310461189 hasConcept C152565575 @default.
• W4310461189 hasConcept C154945302 @default.
• W4310461189 hasConcept C184898388 @default.
• W4310461189 hasConcept C2780980858 @default.
• W4310461189 hasConcept C41008148 @default.
• W4310461189 hasConcept C80444323 @default.
• W4310461189 hasConcept C9357733 @default.
• W4310461189 hasConceptScore W4310461189C108583219 @default.
• W4310461189 hasConceptScore W4310461189C111919701 @default.
• W4310461189 hasConceptScore W4310461189C118505674 @default.
• W4310461189 hasConceptScore W4310461189C119857082 @default.
• W4310461189 hasConceptScore W4310461189C124101348 @default.
• W4310461189 hasConceptScore W4310461189C124952713 @default.
• W4310461189 hasConceptScore W4310461189C132525143 @default.
• W4310461189 hasConceptScore W4310461189C142362112 @default.
• W4310461189 hasConceptScore W4310461189C152565575 @default.
• W4310461189 hasConceptScore W4310461189C154945302 @default.
• W4310461189 hasConceptScore W4310461189C184898388 @default.
• W4310461189 hasConceptScore W4310461189C2780980858 @default.
• W4310461189 hasConceptScore W4310461189C41008148 @default.
• W4310461189 hasConceptScore W4310461189C80444323 @default.
• W4310461189 hasConceptScore W4310461189C9357733 @default.
• W4310461189 hasIssue "7" @default.
• W4310461189 hasLocation W43104611891 @default.
• W4310461189 hasLocation W43104611892 @default.
• W4310461189 hasOpenAccess W4310461189 @default.
• W4310461189 hasPrimaryLocation W43104611891 @default.
• W4310461189 hasRelatedWork W3014300295 @default.
• W4310461189 hasRelatedWork W3164822677 @default.
• W4310461189 hasRelatedWork W4223943233 @default.
• W4310461189 hasRelatedWork W4225161397 @default.
• W4310461189 hasRelatedWork W4250304930 @default.
• W4310461189 hasRelatedWork W4309045103 @default.
• W4310461189 hasRelatedWork W4312200629 @default.
• W4310461189 hasRelatedWork W4360585206 @default.
• W4310461189 hasRelatedWork W4364306694 @default.
• W4310461189 hasRelatedWork W4380086463 @default.
• W4310461189 hasVolume "42" @default.
• W4310461189 isParatext "false" @default.
• W4310461189 isRetracted "false" @default.
• W4310461189 workType "article" @default.