Matches in SemOpenAlex for { <https://semopenalex.org/work/W1853111444> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W1853111444 abstract "Multi-task learning (MTL) improves prediction performance in different contexts by learning models jointly on multiple different, but related tasks. Network data, which are a priori data with a rich relational structure, provide an important context for applying MTL. In particular, the explicit relational structure implies that network data is not i.i.d. data. Network data also often comes with significant metadata (i.e., attributes) associated with each entity (node). Moreover, due to the diversity and variation in network data (e.g., multi-relational links or multi-category entities), various tasks can be performed and often a rich correlation exists between them. Learning algorithms should exploit all of these additional sources of information for better performance. In this work we take a metric-learning point of view for the MTL problem in the network context. Our approach builds on structure preserving metric learning (SPML). In particular SPML learns a Mahalanobis distance metric for node attributes using network structure as supervision, so that the learned distance function encodes the structure and can be used to predict link patterns from attributes. SPML is described for single-task learning on single network. Herein, we propose a multi-task version of SPML, abbreviated as MT-SPML, which is able to learn across multiple related tasks on multiple networks via shared intermediate parametrization. MT-SPML learns a specific metric for each task and a common metric for all tasks. The task correlation is carried through the common metric and the individual metrics encode task specific information. When combined together, they are structure-preserving with respect to individual tasks. MT-SPML works on general networks, thus is suitable for a wide variety of problems. In experiments, we challenge MT-SPML on two real-word problems, where MT-SPML achieves significant improvement." @default.
- W1853111444 created "2016-06-24" @default.
- W1853111444 creator A5051364953 @default.
- W1853111444 creator A5072455364 @default.
- W1853111444 date "2014-11-10" @default.
- W1853111444 modified "2023-10-12" @default.
- W1853111444 title "Multi-Task Metric Learning on Network Data" @default.
- W1853111444 cites W1532499126 @default.
- W1853111444 cites W1888732573 @default.
- W1853111444 cites W1972719705 @default.
- W1853111444 cites W2068965752 @default.
- W1853111444 cites W2094035326 @default.
- W1853111444 cites W2106053110 @default.
- W1853111444 cites W2108544580 @default.
- W1853111444 cites W2108873311 @default.
- W1853111444 cites W2110994494 @default.
- W1853111444 cites W2113573459 @default.
- W1853111444 cites W2125993116 @default.
- W1853111444 cites W2126288184 @default.
- W1853111444 cites W2127345773 @default.
- W1853111444 cites W2143104527 @default.
- W1853111444 cites W2147809096 @default.
- W1853111444 cites W2148522164 @default.
- W1853111444 cites W2155461593 @default.
- W1853111444 cites W2165611133 @default.
- W1853111444 cites W2170682041 @default.
- W1853111444 cites W2420733993 @default.
- W1853111444 cites W2768375068 @default.
- W1853111444 cites W2913340405 @default.
- W1853111444 cites W2962839807 @default.
- W1853111444 doi "https://doi.org/10.48550/arxiv.1411.2337" @default.
- W1853111444 hasPublicationYear "2014" @default.
- W1853111444 type Work @default.
- W1853111444 sameAs 1853111444 @default.
- W1853111444 citedByCount "0" @default.
- W1853111444 crossrefType "posted-content" @default.
- W1853111444 hasAuthorship W1853111444A5051364953 @default.
- W1853111444 hasAuthorship W1853111444A5072455364 @default.
- W1853111444 hasBestOaLocation W18531114441 @default.
- W1853111444 hasConcept C103278499 @default.
- W1853111444 hasConcept C111919701 @default.
- W1853111444 hasConcept C115961682 @default.
- W1853111444 hasConcept C119857082 @default.
- W1853111444 hasConcept C124101348 @default.
- W1853111444 hasConcept C127413603 @default.
- W1853111444 hasConcept C151730666 @default.
- W1853111444 hasConcept C154945302 @default.
- W1853111444 hasConcept C162324750 @default.
- W1853111444 hasConcept C176217482 @default.
- W1853111444 hasConcept C177877439 @default.
- W1853111444 hasConcept C187736073 @default.
- W1853111444 hasConcept C21547014 @default.
- W1853111444 hasConcept C2779343474 @default.
- W1853111444 hasConcept C2780451532 @default.
- W1853111444 hasConcept C41008148 @default.
- W1853111444 hasConcept C5655090 @default.
- W1853111444 hasConcept C62611344 @default.
- W1853111444 hasConcept C66938386 @default.
- W1853111444 hasConcept C86803240 @default.
- W1853111444 hasConcept C93518851 @default.
- W1853111444 hasConceptScore W1853111444C103278499 @default.
- W1853111444 hasConceptScore W1853111444C111919701 @default.
- W1853111444 hasConceptScore W1853111444C115961682 @default.
- W1853111444 hasConceptScore W1853111444C119857082 @default.
- W1853111444 hasConceptScore W1853111444C124101348 @default.
- W1853111444 hasConceptScore W1853111444C127413603 @default.
- W1853111444 hasConceptScore W1853111444C151730666 @default.
- W1853111444 hasConceptScore W1853111444C154945302 @default.
- W1853111444 hasConceptScore W1853111444C162324750 @default.
- W1853111444 hasConceptScore W1853111444C176217482 @default.
- W1853111444 hasConceptScore W1853111444C177877439 @default.
- W1853111444 hasConceptScore W1853111444C187736073 @default.
- W1853111444 hasConceptScore W1853111444C21547014 @default.
- W1853111444 hasConceptScore W1853111444C2779343474 @default.
- W1853111444 hasConceptScore W1853111444C2780451532 @default.
- W1853111444 hasConceptScore W1853111444C41008148 @default.
- W1853111444 hasConceptScore W1853111444C5655090 @default.
- W1853111444 hasConceptScore W1853111444C62611344 @default.
- W1853111444 hasConceptScore W1853111444C66938386 @default.
- W1853111444 hasConceptScore W1853111444C86803240 @default.
- W1853111444 hasConceptScore W1853111444C93518851 @default.
- W1853111444 hasLocation W18531114441 @default.
- W1853111444 hasLocation W18531114442 @default.
- W1853111444 hasLocation W18531114443 @default.
- W1853111444 hasOpenAccess W1853111444 @default.
- W1853111444 hasPrimaryLocation W18531114441 @default.
- W1853111444 hasRelatedWork W1549959306 @default.
- W1853111444 hasRelatedWork W2001007279 @default.
- W1853111444 hasRelatedWork W2079674650 @default.
- W1853111444 hasRelatedWork W2112176619 @default.
- W1853111444 hasRelatedWork W2212764924 @default.
- W1853111444 hasRelatedWork W2389834944 @default.
- W1853111444 hasRelatedWork W2806326686 @default.
- W1853111444 hasRelatedWork W2945061532 @default.
- W1853111444 hasRelatedWork W3181676408 @default.
- W1853111444 hasRelatedWork W320292658 @default.
- W1853111444 isParatext "false" @default.
- W1853111444 isRetracted "false" @default.
- W1853111444 magId "1853111444" @default.
- W1853111444 workType "article" @default.