FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2343790552> ?p ?o ?g. }

• W2343790552 endingPage "758" @default.
• W2343790552 startingPage "744" @default.
• W2343790552 abstract "Multitask learning (MTL) is commonly used for jointly optimizing multiple learning tasks. To date, all existing MTL methods have been designed for tasks with feature-vector represented instances, but cannot be applied to structure data, such as graphs. More importantly, when carrying out MTL, existing methods mainly focus on exploring overall commonality or disparity between tasks for learning, but cannot explicitly capture task relationships in the feature space, so they are unable to answer important questions, such as what exactly is shared between tasks and what is the uniqueness of one task differing from others? In this paper, we formulate a new multitask graph learning problem, and propose a task sensitive feature exploration and learning algorithm for multitask graph classification. Because graphs do not have features available, we advocate a task sensitive feature exploration and learning paradigm to jointly discover discriminative subgraph features across different tasks. In addition, a feature learning process is carried out to categorize each subgraph feature into one of three categories: (1) common feature; (2) task auxiliary feature; and (3) task specific feature, indicating whether the feature is shared by all tasks, by a subset of tasks, or by only one specific task, respectively. The feature learning and the multiple task learning are iteratively optimized to form a multitask graph classification model with a global optimization goal. Experiments on real-world functional brain analysis and chemical compound categorization demonstrate the algorithm's performance. Results confirm that our method can be used to explicitly capture task correlations and uniqueness in the feature space, and explicitly answer what are shared between tasks and what is the uniqueness of a specific task." @default.
• W2343790552 created "2016-06-24" @default.
• W2343790552 creator A5007475662 @default.
• W2343790552 creator A5008056593 @default.
• W2343790552 creator A5059227406 @default.
• W2343790552 creator A5074852078 @default.
• W2343790552 creator A5084641325 @default.
• W2343790552 date "2017-03-01" @default.
• W2343790552 modified "2023-10-17" @default.
• W2343790552 title "Task Sensitive Feature Exploration and Learning for Multitask Graph Classification" @default.
• W2343790552 cites W1524882660 @default.
• W2343790552 cites W1585952056 @default.
• W2343790552 cites W195071355 @default.
• W2343790552 cites W1971039378 @default.
• W2343790552 cites W1974099839 @default.
• W2343790552 cites W2009746375 @default.
• W2343790552 cites W2014886698 @default.
• W2343790552 cites W2015342278 @default.
• W2343790552 cites W2016210016 @default.
• W2343790552 cites W2016440973 @default.
• W2343790552 cites W2029901035 @default.
• W2343790552 cites W2032612424 @default.
• W2343790552 cites W2042891941 @default.
• W2343790552 cites W2054093027 @default.
• W2343790552 cites W2069808690 @default.
• W2343790552 cites W2070002549 @default.
• W2343790552 cites W2072336646 @default.
• W2343790552 cites W2077140561 @default.
• W2343790552 cites W2078789330 @default.
• W2343790552 cites W2089514923 @default.
• W2343790552 cites W2098711149 @default.
• W2343790552 cites W2102039273 @default.
• W2343790552 cites W2105869081 @default.
• W2343790552 cites W2107793528 @default.
• W2343790552 cites W2108718322 @default.
• W2343790552 cites W2109363337 @default.
• W2343790552 cites W2112837588 @default.
• W2343790552 cites W2113014179 @default.
• W2343790552 cites W2114062029 @default.
• W2343790552 cites W2122457251 @default.
• W2343790552 cites W2135588188 @default.
• W2343790552 cites W2137609262 @default.
• W2343790552 cites W2143104527 @default.
• W2343790552 cites W2143426320 @default.
• W2343790552 cites W2145388307 @default.
• W2343790552 cites W2148611932 @default.
• W2343790552 cites W2154881938 @default.
• W2343790552 cites W2157825442 @default.
• W2343790552 cites W2161723275 @default.
• W2343790552 cites W2164281374 @default.
• W2343790552 cites W2165698076 @default.
• W2343790552 cites W2174772062 @default.
• W2343790552 cites W817531966 @default.
• W2343790552 doi "https://doi.org/10.1109/tcyb.2016.2526058" @default.
• W2343790552 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26978839" @default.
• W2343790552 hasPublicationYear "2017" @default.
• W2343790552 type Work @default.
• W2343790552 sameAs 2343790552 @default.
• W2343790552 citedByCount "55" @default.
• W2343790552 countsByYear W23437905522017 @default.
• W2343790552 countsByYear W23437905522018 @default.
• W2343790552 countsByYear W23437905522019 @default.
• W2343790552 countsByYear W23437905522020 @default.
• W2343790552 countsByYear W23437905522021 @default.
• W2343790552 countsByYear W23437905522022 @default.
• W2343790552 countsByYear W23437905522023 @default.
• W2343790552 crossrefType "journal-article" @default.
• W2343790552 hasAuthorship W2343790552A5007475662 @default.
• W2343790552 hasAuthorship W2343790552A5008056593 @default.
• W2343790552 hasAuthorship W2343790552A5059227406 @default.
• W2343790552 hasAuthorship W2343790552A5074852078 @default.
• W2343790552 hasAuthorship W2343790552A5084641325 @default.
• W2343790552 hasBestOaLocation W23437905522 @default.
• W2343790552 hasConcept C119857082 @default.
• W2343790552 hasConcept C132525143 @default.
• W2343790552 hasConcept C138885662 @default.
• W2343790552 hasConcept C153180895 @default.
• W2343790552 hasConcept C154945302 @default.
• W2343790552 hasConcept C162324750 @default.
• W2343790552 hasConcept C187736073 @default.
• W2343790552 hasConcept C2776401178 @default.
• W2343790552 hasConcept C2780451532 @default.
• W2343790552 hasConcept C28006648 @default.
• W2343790552 hasConcept C41008148 @default.
• W2343790552 hasConcept C41895202 @default.
• W2343790552 hasConcept C59404180 @default.
• W2343790552 hasConcept C80444323 @default.
• W2343790552 hasConcept C83665646 @default.
• W2343790552 hasConcept C94124525 @default.
• W2343790552 hasConcept C97931131 @default.
• W2343790552 hasConceptScore W2343790552C119857082 @default.
• W2343790552 hasConceptScore W2343790552C132525143 @default.
• W2343790552 hasConceptScore W2343790552C138885662 @default.
• W2343790552 hasConceptScore W2343790552C153180895 @default.
• W2343790552 hasConceptScore W2343790552C154945302 @default.
• W2343790552 hasConceptScore W2343790552C162324750 @default.
• W2343790552 hasConceptScore W2343790552C187736073 @default.
• W2343790552 hasConceptScore W2343790552C2776401178 @default.

• next