FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136709090> ?p ?o ?g. }

• W3136709090 abstract "Multi-label classification (MC) is a standard machine learning problem in which a data point can be associated with a set of classes. A more challenging scenario is given by hierarchical multi-label classification (HMC) problems, in which every prediction must satisfy a given set of hard constraints expressing subclass relationships between classes. In this paper, we propose C-HMCNN(h), a novel approach for solving HMC problems, which, given a network h for the underlying MC problem, exploits the hierarchy information in order to produce predictions coherent with the constraints and to improve performance. Furthermore, we extend the logic used to express HMC constraints in order to be able to specify more complex relations among the classes and propose a new model CCN(h), which extends C-HMCNN(h) and is again able to satisfy and exploit the constraints to improve performance. We conduct an extensive experimental analysis showing the superior performance of both C-HMCNN(h) and CCN(h) when compared to state-of-the-art models in both the HMC and the general MC setting with hard logical constraints." @default.
• W3136709090 created "2021-03-29" @default.
• W3136709090 creator A5004609930 @default.
• W3136709090 creator A5091549352 @default.
• W3136709090 date "2021-03-24" @default.
• W3136709090 modified "2023-09-25" @default.
• W3136709090 title "Multi-Label Classification Neural Networks with Hard Logical Constraints." @default.
• W3136709090 cites W1506285740 @default.
• W3136709090 cites W1534416612 @default.
• W3136709090 cites W1565746575 @default.
• W3136709090 cites W1603920809 @default.
• W3136709090 cites W1669104078 @default.
• W3136709090 cites W1672891595 @default.
• W3136709090 cites W1693343509 @default.
• W3136709090 cites W1756265184 @default.
• W3136709090 cites W1870686808 @default.
• W3136709090 cites W1953606363 @default.
• W3136709090 cites W1963990555 @default.
• W3136709090 cites W1967542092 @default.
• W3136709090 cites W1974287593 @default.
• W3136709090 cites W1980179845 @default.
• W3136709090 cites W2007483518 @default.
• W3136709090 cites W2052684427 @default.
• W3136709090 cites W2061453990 @default.
• W3136709090 cites W2064675550 @default.
• W3136709090 cites W2077658674 @default.
• W3136709090 cites W2108598243 @default.
• W3136709090 cites W2111353076 @default.
• W3136709090 cites W2116373735 @default.
• W3136709090 cites W2118712128 @default.
• W3136709090 cites W2121526711 @default.
• W3136709090 cites W2123217057 @default.
• W3136709090 cites W2124396699 @default.
• W3136709090 cites W2127723919 @default.
• W3136709090 cites W2131984901 @default.
• W3136709090 cites W2135140174 @default.
• W3136709090 cites W2135569230 @default.
• W3136709090 cites W2150102617 @default.
• W3136709090 cites W2150766729 @default.
• W3136709090 cites W2156386646 @default.
• W3136709090 cites W2156935079 @default.
• W3136709090 cites W2165073069 @default.
• W3136709090 cites W2166985665 @default.
• W3136709090 cites W2181432155 @default.
• W3136709090 cites W2182822465 @default.
• W3136709090 cites W2201744460 @default.
• W3136709090 cites W2520368209 @default.
• W3136709090 cites W2565304260 @default.
• W3136709090 cites W2586665457 @default.
• W3136709090 cites W2782959635 @default.
• W3136709090 cites W2803270043 @default.
• W3136709090 cites W2896109759 @default.
• W3136709090 cites W2904828343 @default.
• W3136709090 cites W2908663744 @default.
• W3136709090 cites W2910644300 @default.
• W3136709090 cites W2949276121 @default.
• W3136709090 cites W2963019788 @default.
• W3136709090 cites W2963277062 @default.
• W3136709090 cites W2963687836 @default.
• W3136709090 cites W2963737801 @default.
• W3136709090 cites W2964121744 @default.
• W3136709090 cites W2964281107 @default.
• W3136709090 cites W2977069059 @default.
• W3136709090 cites W2982138961 @default.
• W3136709090 cites W2989202311 @default.
• W3136709090 cites W3036286896 @default.
• W3136709090 cites W3104057403 @default.
• W3136709090 cites W3117784687 @default.
• W3136709090 cites W31561947 @default.
• W3136709090 cites W64813323 @default.
• W3136709090 hasPublicationYear "2021" @default.
• W3136709090 type Work @default.
• W3136709090 sameAs 3136709090 @default.
• W3136709090 citedByCount "0" @default.
• W3136709090 crossrefType "posted-content" @default.
• W3136709090 hasAuthorship W3136709090A5004609930 @default.
• W3136709090 hasAuthorship W3136709090A5091549352 @default.
• W3136709090 hasConcept C11413529 @default.
• W3136709090 hasConcept C119857082 @default.
• W3136709090 hasConcept C154945302 @default.
• W3136709090 hasConcept C162324750 @default.
• W3136709090 hasConcept C165696696 @default.
• W3136709090 hasConcept C177264268 @default.
• W3136709090 hasConcept C199360897 @default.
• W3136709090 hasConcept C2524010 @default.
• W3136709090 hasConcept C2776482837 @default.
• W3136709090 hasConcept C28719098 @default.
• W3136709090 hasConcept C31170391 @default.
• W3136709090 hasConcept C33923547 @default.
• W3136709090 hasConcept C34447519 @default.
• W3136709090 hasConcept C38652104 @default.
• W3136709090 hasConcept C41008148 @default.
• W3136709090 hasConcept C50644808 @default.
• W3136709090 hasConcept C80444323 @default.
• W3136709090 hasConceptScore W3136709090C11413529 @default.
• W3136709090 hasConceptScore W3136709090C119857082 @default.
• W3136709090 hasConceptScore W3136709090C154945302 @default.
• W3136709090 hasConceptScore W3136709090C162324750 @default.
• W3136709090 hasConceptScore W3136709090C165696696 @default.
• W3136709090 hasConceptScore W3136709090C177264268 @default.

• next