Matches in SemOpenAlex for { <https://semopenalex.org/work/W1980095847> ?p ?o ?g. }
- W1980095847 abstract "Link prediction is a fundamental task in statistical analysis of network data. Though much research has concentrated on predicting entity-entity relationships in homogeneous networks, it has attracted increasing attentions to predict relationships in heterogeneous networks, which consist of multiple types of nodes and relational links. Existing work on heterogeneous network link prediction mainly focuses on using input features that are explicitly extracted by humans. This paper presents an approach to automatically learn latent features from partially observed heterogeneous networks, with a particular focus on entity-attribute networks (EANs), and making predictions for unseen pairs. To make the latent features discriminative, we adopt the max-margin idea under the framework of maximum entropy discrimination (MED). Our maximum entropy discrimination joint relational model (MED-JRM) can jointly predict entity-entity relationships as well as the missing attributes of entities in EANs. Experimental results on several real networks demonstrate that our model has improved performance over state-of-the-art homogeneous and heterogeneous network link prediction algorithms." @default.
- W1980095847 created "2016-06-24" @default.
- W1980095847 creator A5003713785 @default.
- W1980095847 creator A5022525223 @default.
- W1980095847 creator A5037717179 @default.
- W1980095847 creator A5047876033 @default.
- W1980095847 creator A5080298585 @default.
- W1980095847 date "2014-07-01" @default.
- W1980095847 modified "2023-09-23" @default.
- W1980095847 title "Max-margin latent feature relational models for entity-attribute networks" @default.
- W1980095847 cites W103340358 @default.
- W1980095847 cites W140573599 @default.
- W1980095847 cites W1553830511 @default.
- W1980095847 cites W1979104937 @default.
- W1980095847 cites W2003707464 @default.
- W1980095847 cites W2025605741 @default.
- W1980095847 cites W2066459332 @default.
- W1980095847 cites W2071018679 @default.
- W1980095847 cites W2088571412 @default.
- W1980095847 cites W2092912084 @default.
- W1980095847 cites W2095054612 @default.
- W1980095847 cites W2096989558 @default.
- W1980095847 cites W2099537822 @default.
- W1980095847 cites W2100931213 @default.
- W1980095847 cites W2100960788 @default.
- W1980095847 cites W2101101940 @default.
- W1980095847 cites W2103133870 @default.
- W1980095847 cites W2106813372 @default.
- W1980095847 cites W2107569009 @default.
- W1980095847 cites W2123549998 @default.
- W1980095847 cites W2125082260 @default.
- W1980095847 cites W2128002512 @default.
- W1980095847 cites W2133299088 @default.
- W1980095847 cites W2133568543 @default.
- W1980095847 cites W2136116685 @default.
- W1980095847 cites W2137793309 @default.
- W1980095847 cites W2151498529 @default.
- W1980095847 cites W2151965738 @default.
- W1980095847 cites W2158535911 @default.
- W1980095847 cites W2159203990 @default.
- W1980095847 cites W2161813919 @default.
- W1980095847 cites W2162422091 @default.
- W1980095847 cites W2162630660 @default.
- W1980095847 cites W2168190036 @default.
- W1980095847 cites W2420733993 @default.
- W1980095847 cites W2768375068 @default.
- W1980095847 cites W2962814162 @default.
- W1980095847 cites W34646664 @default.
- W1980095847 doi "https://doi.org/10.1109/ijcnn.2014.6889508" @default.
- W1980095847 hasPublicationYear "2014" @default.
- W1980095847 type Work @default.
- W1980095847 sameAs 1980095847 @default.
- W1980095847 citedByCount "0" @default.
- W1980095847 crossrefType "proceedings-article" @default.
- W1980095847 hasAuthorship W1980095847A5003713785 @default.
- W1980095847 hasAuthorship W1980095847A5022525223 @default.
- W1980095847 hasAuthorship W1980095847A5037717179 @default.
- W1980095847 hasAuthorship W1980095847A5047876033 @default.
- W1980095847 hasAuthorship W1980095847A5080298585 @default.
- W1980095847 hasConcept C106301342 @default.
- W1980095847 hasConcept C114614502 @default.
- W1980095847 hasConcept C119857082 @default.
- W1980095847 hasConcept C121332964 @default.
- W1980095847 hasConcept C124101348 @default.
- W1980095847 hasConcept C138885662 @default.
- W1980095847 hasConcept C154945302 @default.
- W1980095847 hasConcept C2776401178 @default.
- W1980095847 hasConcept C33923547 @default.
- W1980095847 hasConcept C41008148 @default.
- W1980095847 hasConcept C41895202 @default.
- W1980095847 hasConcept C5655090 @default.
- W1980095847 hasConcept C62520636 @default.
- W1980095847 hasConcept C66882249 @default.
- W1980095847 hasConcept C774472 @default.
- W1980095847 hasConcept C9679016 @default.
- W1980095847 hasConcept C97931131 @default.
- W1980095847 hasConceptScore W1980095847C106301342 @default.
- W1980095847 hasConceptScore W1980095847C114614502 @default.
- W1980095847 hasConceptScore W1980095847C119857082 @default.
- W1980095847 hasConceptScore W1980095847C121332964 @default.
- W1980095847 hasConceptScore W1980095847C124101348 @default.
- W1980095847 hasConceptScore W1980095847C138885662 @default.
- W1980095847 hasConceptScore W1980095847C154945302 @default.
- W1980095847 hasConceptScore W1980095847C2776401178 @default.
- W1980095847 hasConceptScore W1980095847C33923547 @default.
- W1980095847 hasConceptScore W1980095847C41008148 @default.
- W1980095847 hasConceptScore W1980095847C41895202 @default.
- W1980095847 hasConceptScore W1980095847C5655090 @default.
- W1980095847 hasConceptScore W1980095847C62520636 @default.
- W1980095847 hasConceptScore W1980095847C66882249 @default.
- W1980095847 hasConceptScore W1980095847C774472 @default.
- W1980095847 hasConceptScore W1980095847C9679016 @default.
- W1980095847 hasConceptScore W1980095847C97931131 @default.
- W1980095847 hasLocation W19800958471 @default.
- W1980095847 hasOpenAccess W1980095847 @default.
- W1980095847 hasPrimaryLocation W19800958471 @default.
- W1980095847 hasRelatedWork W1971623867 @default.
- W1980095847 hasRelatedWork W2213006595 @default.
- W1980095847 hasRelatedWork W2554403468 @default.
- W1980095847 hasRelatedWork W2573132524 @default.