Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952802231> ?p ?o ?g. }
- W2952802231 abstract "Semi-Non-negative Matrix Factorization is a technique that learns a low-dimensional representation of a dataset that lends itself to a clustering interpretation. It is possible that the mapping between this new representation and our original data matrix contains rather complex hierarchical information with implicit lower-level hidden attributes, that classical one level clustering methodologies can not interpret. In this work we propose a novel model, Deep Semi-NMF, that is able to learn such hidden representations that allow themselves to an interpretation of clustering according to different, unknown attributes of a given dataset. We also present a semi-supervised version of the algorithm, named Deep WSF, that allows the use of (partial) prior information for each of the known attributes of a dataset, that allows the model to be used on datasets with mixed attribute knowledge. Finally, we show that our models are able to learn low-dimensional representations that are better suited for clustering, but also classification, outperforming Semi-Non-negative Matrix Factorization, but also other state-of-the-art methodologies variants." @default.
- W2952802231 created "2019-06-27" @default.
- W2952802231 creator A5033198464 @default.
- W2952802231 creator A5052703085 @default.
- W2952802231 creator A5079462322 @default.
- W2952802231 creator A5080553022 @default.
- W2952802231 date "2015-09-10" @default.
- W2952802231 modified "2023-09-27" @default.
- W2952802231 title "A deep matrix factorization method for learning attribute representations" @default.
- W2952802231 cites W1589331344 @default.
- W2952802231 cites W1972490990 @default.
- W2952802231 cites W1991380130 @default.
- W2952802231 cites W2006793117 @default.
- W2952802231 cites W2015583498 @default.
- W2952802231 cites W2058961190 @default.
- W2952802231 cites W2059745395 @default.
- W2952802231 cites W2066680326 @default.
- W2952802231 cites W2078841894 @default.
- W2952802231 cites W2079196839 @default.
- W2952802231 cites W2094087561 @default.
- W2952802231 cites W2099629511 @default.
- W2952802231 cites W2100495367 @default.
- W2952802231 cites W2104290444 @default.
- W2952802231 cites W2108119513 @default.
- W2952802231 cites W2122932202 @default.
- W2952802231 cites W2129354191 @default.
- W2952802231 cites W2132692097 @default.
- W2952802231 cites W2136171036 @default.
- W2952802231 cites W2136787567 @default.
- W2952802231 cites W2137477262 @default.
- W2952802231 cites W2137540340 @default.
- W2952802231 cites W2137983211 @default.
- W2952802231 cites W2138451337 @default.
- W2952802231 cites W2142621404 @default.
- W2952802231 cites W2146482778 @default.
- W2952802231 cites W2149194912 @default.
- W2952802231 cites W2155151262 @default.
- W2952802231 cites W2156718197 @default.
- W2952802231 cites W2168103112 @default.
- W2952802231 cites W2237846767 @default.
- W2952802231 cites W2571268788 @default.
- W2952802231 cites W2964322446 @default.
- W2952802231 hasPublicationYear "2015" @default.
- W2952802231 type Work @default.
- W2952802231 sameAs 2952802231 @default.
- W2952802231 citedByCount "0" @default.
- W2952802231 crossrefType "posted-content" @default.
- W2952802231 hasAuthorship W2952802231A5033198464 @default.
- W2952802231 hasAuthorship W2952802231A5052703085 @default.
- W2952802231 hasAuthorship W2952802231A5079462322 @default.
- W2952802231 hasAuthorship W2952802231A5080553022 @default.
- W2952802231 hasConcept C106487976 @default.
- W2952802231 hasConcept C108583219 @default.
- W2952802231 hasConcept C119857082 @default.
- W2952802231 hasConcept C121332964 @default.
- W2952802231 hasConcept C124101348 @default.
- W2952802231 hasConcept C152671427 @default.
- W2952802231 hasConcept C153180895 @default.
- W2952802231 hasConcept C154945302 @default.
- W2952802231 hasConcept C158693339 @default.
- W2952802231 hasConcept C159985019 @default.
- W2952802231 hasConcept C17744445 @default.
- W2952802231 hasConcept C192562407 @default.
- W2952802231 hasConcept C199360897 @default.
- W2952802231 hasConcept C199539241 @default.
- W2952802231 hasConcept C2776359362 @default.
- W2952802231 hasConcept C41008148 @default.
- W2952802231 hasConcept C42355184 @default.
- W2952802231 hasConcept C527412718 @default.
- W2952802231 hasConcept C62520636 @default.
- W2952802231 hasConcept C73555534 @default.
- W2952802231 hasConcept C94625758 @default.
- W2952802231 hasConceptScore W2952802231C106487976 @default.
- W2952802231 hasConceptScore W2952802231C108583219 @default.
- W2952802231 hasConceptScore W2952802231C119857082 @default.
- W2952802231 hasConceptScore W2952802231C121332964 @default.
- W2952802231 hasConceptScore W2952802231C124101348 @default.
- W2952802231 hasConceptScore W2952802231C152671427 @default.
- W2952802231 hasConceptScore W2952802231C153180895 @default.
- W2952802231 hasConceptScore W2952802231C154945302 @default.
- W2952802231 hasConceptScore W2952802231C158693339 @default.
- W2952802231 hasConceptScore W2952802231C159985019 @default.
- W2952802231 hasConceptScore W2952802231C17744445 @default.
- W2952802231 hasConceptScore W2952802231C192562407 @default.
- W2952802231 hasConceptScore W2952802231C199360897 @default.
- W2952802231 hasConceptScore W2952802231C199539241 @default.
- W2952802231 hasConceptScore W2952802231C2776359362 @default.
- W2952802231 hasConceptScore W2952802231C41008148 @default.
- W2952802231 hasConceptScore W2952802231C42355184 @default.
- W2952802231 hasConceptScore W2952802231C527412718 @default.
- W2952802231 hasConceptScore W2952802231C62520636 @default.
- W2952802231 hasConceptScore W2952802231C73555534 @default.
- W2952802231 hasConceptScore W2952802231C94625758 @default.
- W2952802231 hasLocation W29528022311 @default.
- W2952802231 hasOpenAccess W2952802231 @default.
- W2952802231 hasPrimaryLocation W29528022311 @default.
- W2952802231 hasRelatedWork W1154172097 @default.
- W2952802231 hasRelatedWork W1495279923 @default.
- W2952802231 hasRelatedWork W1502786745 @default.
- W2952802231 hasRelatedWork W1745685099 @default.