?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Decentralized+Learning+with+Budgeted+Network+Load+Using+Gaussian+Copulas+and+Classifier+Ensembles.&rft.creator=Klein%2C+J&rft.creator=Albardan%2C+M&rft.creator=Guedj%2C+B&rft.creator=Colot%2C+O&rft.description=We+examine+a+network+of+learners+which+address+the+same+classification+task+but+must+learn+from+different+data+sets.+The+learners+cannot+share+data+but+instead+share+their+models.+Models+are+shared+only+one+time+so+as+to+preserve+the+network+load.+We+introduce+DELCO+(standing+for+Decentralized+Ensemble+Learning+with+COpulas)%2C+a+new+approach+allowing+to+aggregate+the+predictions+of+the+classifiers+trained+by+each+learner.+The+proposed+method+aggregates+the+base+classifiers+using+a+probabilistic+model+relying+on+Gaussian+copulas.+Experiments+on+logistic+regressor+ensembles+demonstrate+competing+accuracy+and+increased+robustness+in+case+of+dependent+classifiers.+A+companion+python+implementation+can+be+downloaded+at+https%3A%2F%2Fgithub.com%2Fjohn-klein%2FDELCO.&rft.subject=Decentralized+learning%2C+Classifier+ensemble%2C+Copulas&rft.publisher=Springer&rft.contributor=Cellier%2C+P&rft.contributor=Driessens%2C+K&rft.date=2019-03-28&rft.type=Proceedings+paper&rft.language=eng&rft.source=+++++In%3A+Cellier%2C+P+and+Driessens%2C+K%2C+(eds.)+Machine+Learning+and+Knowledge+Discovery+in+Databases.+ECML+PKDD+2019.+Communications+in+Computer+and+Information+Science.++(pp.+pp.+301-316).++Springer%3A+Cham.+(2019)+++++&rft.format=text&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10095178%2F1%2F1804.10028v3.pdf&rft.identifier=https%3A%2F%2Fdiscovery.ucl.ac.uk%2Fid%2Feprint%2F10095178%2F&rft.rights=open