FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186522488> ?p ?o ?g. }

• W3186522488 endingPage "291" @default.
• W3186522488 startingPage "281" @default.
• W3186522488 abstract "Bayesian Networks have been widely used in the last decades in many fields, to describe statistical dependencies among random variables. In general, learning the structure of such models is a problem with considerable theoretical interest that poses many challenges. On the one hand, it is a well-known NP-complete problem, practically hardened by the huge search space of possible solutions. On the other hand, the phenomenon of I-equivalence, i.e., different graphical structures underpinning the same set of statistical dependencies, may lead to multimodal fitness landscapes further hindering maximum likelihood approaches to solve the task. Despite all these difficulties, greedy search methods based on a likelihood score coupled with a regularizator score to account for model complexity, have been shown to be surprisingly effective in practice. In this paper, we consider the formulation of the task of learning the structure of Bayesian Networks as an optimization problem based on a likelihood score, without complexity terms to regularize it. In particular, we exploit the NSGA-II multi-objective optimization procedure in order to explicitly account for both the likelihood of a solution and the number of selected arcs, by setting these as the two objective functions of the method. The aim of this work is to investigate the behavior of NSGA-II and analyse the quality of its solutions. We thus thoroughly examined the optimization results obtained on a wide set of simulated data, by considering both the goodness of the inferred solutions in terms of the objective functions values achieved, and by comparing the retrieved structures with the ground truth, i.e., the networks used to generate the target data. Our results show that NSGA-II can converge to solutions characterized by better likelihood and less arcs than classic approaches, although paradoxically characterized in many cases by a lower similarity with the target network." @default.
• W3186522488 created "2021-08-02" @default.
• W3186522488 creator A5013723473 @default.
• W3186522488 creator A5022687646 @default.
• W3186522488 creator A5043650939 @default.
• W3186522488 date "2021-10-01" @default.
• W3186522488 modified "2023-09-27" @default.
• W3186522488 title "Investigating the performance of multi-objective optimization when learning Bayesian Networks" @default.
• W3186522488 cites W1530964327 @default.
• W3186522488 cites W1970687027 @default.
• W3186522488 cites W2022485595 @default.
• W3186522488 cites W2073307618 @default.
• W3186522488 cites W2076753758 @default.
• W3186522488 cites W2105241511 @default.
• W3186522488 cites W2106334424 @default.
• W3186522488 cites W2126105956 @default.
• W3186522488 cites W2128088446 @default.
• W3186522488 cites W2142635246 @default.
• W3186522488 cites W2160088187 @default.
• W3186522488 cites W2161632986 @default.
• W3186522488 cites W2168175751 @default.
• W3186522488 cites W2209688796 @default.
• W3186522488 cites W2262800383 @default.
• W3186522488 cites W2571455846 @default.
• W3186522488 cites W2573268273 @default.
• W3186522488 cites W2590081572 @default.
• W3186522488 cites W2705490344 @default.
• W3186522488 cites W2770650282 @default.
• W3186522488 cites W2795386130 @default.
• W3186522488 cites W2799451098 @default.
• W3186522488 cites W2885291112 @default.
• W3186522488 cites W2897562111 @default.
• W3186522488 cites W2979638007 @default.
• W3186522488 cites W3099878876 @default.
• W3186522488 cites W3144824798 @default.
• W3186522488 doi "https://doi.org/10.1016/j.neucom.2021.07.049" @default.
• W3186522488 hasPublicationYear "2021" @default.
• W3186522488 type Work @default.
• W3186522488 sameAs 3186522488 @default.
• W3186522488 citedByCount "1" @default.
• W3186522488 countsByYear W31865224882023 @default.
• W3186522488 crossrefType "journal-article" @default.
• W3186522488 hasAuthorship W3186522488A5013723473 @default.
• W3186522488 hasAuthorship W3186522488A5022687646 @default.
• W3186522488 hasAuthorship W3186522488A5043650939 @default.
• W3186522488 hasBestOaLocation W31865224882 @default.
• W3186522488 hasConcept C11413529 @default.
• W3186522488 hasConcept C118615104 @default.
• W3186522488 hasConcept C119857082 @default.
• W3186522488 hasConcept C126255220 @default.
• W3186522488 hasConcept C137836250 @default.
• W3186522488 hasConcept C154945302 @default.
• W3186522488 hasConcept C177264268 @default.
• W3186522488 hasConcept C199360897 @default.
• W3186522488 hasConcept C2778049539 @default.
• W3186522488 hasConcept C2780069185 @default.
• W3186522488 hasConcept C33724603 @default.
• W3186522488 hasConcept C33923547 @default.
• W3186522488 hasConcept C41008148 @default.
• W3186522488 hasConceptScore W3186522488C11413529 @default.
• W3186522488 hasConceptScore W3186522488C118615104 @default.
• W3186522488 hasConceptScore W3186522488C119857082 @default.
• W3186522488 hasConceptScore W3186522488C126255220 @default.
• W3186522488 hasConceptScore W3186522488C137836250 @default.
• W3186522488 hasConceptScore W3186522488C154945302 @default.
• W3186522488 hasConceptScore W3186522488C177264268 @default.
• W3186522488 hasConceptScore W3186522488C199360897 @default.
• W3186522488 hasConceptScore W3186522488C2778049539 @default.
• W3186522488 hasConceptScore W3186522488C2780069185 @default.
• W3186522488 hasConceptScore W3186522488C33724603 @default.
• W3186522488 hasConceptScore W3186522488C33923547 @default.
• W3186522488 hasConceptScore W3186522488C41008148 @default.
• W3186522488 hasLocation W31865224881 @default.
• W3186522488 hasLocation W31865224882 @default.
• W3186522488 hasOpenAccess W3186522488 @default.
• W3186522488 hasPrimaryLocation W31865224881 @default.
• W3186522488 hasRelatedWork W2974398825 @default.
• W3186522488 hasRelatedWork W3154094704 @default.
• W3186522488 hasRelatedWork W3188540459 @default.
• W3186522488 hasRelatedWork W3195699808 @default.
• W3186522488 hasRelatedWork W3199608561 @default.
• W3186522488 hasRelatedWork W4210854019 @default.
• W3186522488 hasRelatedWork W4306295037 @default.
• W3186522488 hasRelatedWork W4312405383 @default.
• W3186522488 hasRelatedWork W4322750901 @default.
• W3186522488 hasRelatedWork W990771678 @default.
• W3186522488 hasVolume "461" @default.
• W3186522488 isParatext "false" @default.
• W3186522488 isRetracted "false" @default.
• W3186522488 magId "3186522488" @default.
• W3186522488 workType "article" @default.