Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202375299> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3202375299 endingPage "553" @default.
- W3202375299 startingPage "538" @default.
- W3202375299 abstract "Deep multi-task learning attracts much attention in recent years as it achieves good performance in many applications. Feature learning is important to deep multi-task learning for sharing common information among tasks. In this paper, we propose a Hierarchical Graph Neural Network (HGNN) to learn augmented features for deep multi-task learning. The HGNN consists of two-level graph neural networks. In the low level, an intra-task graph neural network is responsible of learning a powerful representation for each data point in a task by aggregating its neighbors. Based on the learned representation, a task embedding can be generated for each task in a similar way to max pooling. In the second level, an inter-task graph neural network updates task embeddings of all the tasks based on the attention mechanism to model task relations. Then the task embedding of one task is used to augment the feature representation of data points in this task. Moreover, for classification tasks, an inter-class graph neural network is introduced to conduct similar operations on a finer granularity, i.e., the class level, to generate class embeddings for each class in all the tasks using class embeddings to augment the feature representation. The proposed feature augmentation strategy can be used in many deep multi-task learning models. Experiments on real-world datasets show the significant performance improvement when using this strategy." @default.
- W3202375299 created "2021-10-11" @default.
- W3202375299 creator A5023086649 @default.
- W3202375299 creator A5024258334 @default.
- W3202375299 creator A5052124868 @default.
- W3202375299 creator A5053905081 @default.
- W3202375299 creator A5071773009 @default.
- W3202375299 date "2021-01-01" @default.
- W3202375299 modified "2023-10-16" @default.
- W3202375299 title "Deep Multi-task Augmented Feature Learning via Hierarchical Graph Neural Network" @default.
- W3202375299 cites W1958932515 @default.
- W3202375299 cites W2051464482 @default.
- W3202375299 cites W2052678124 @default.
- W3202375299 cites W2117539524 @default.
- W3202375299 cites W2133491790 @default.
- W3202375299 cites W2138228305 @default.
- W3202375299 cites W2394550695 @default.
- W3202375299 cites W2510867321 @default.
- W3202375299 cites W2561587488 @default.
- W3202375299 cites W2627183927 @default.
- W3202375299 cites W2896190342 @default.
- W3202375299 cites W2913340405 @default.
- W3202375299 cites W2963430933 @default.
- W3202375299 cites W2963788376 @default.
- W3202375299 cites W2963877604 @default.
- W3202375299 cites W3034704453 @default.
- W3202375299 cites W4149471 @default.
- W3202375299 doi "https://doi.org/10.1007/978-3-030-86486-6_33" @default.
- W3202375299 hasPublicationYear "2021" @default.
- W3202375299 type Work @default.
- W3202375299 sameAs 3202375299 @default.
- W3202375299 citedByCount "5" @default.
- W3202375299 countsByYear W32023752992020 @default.
- W3202375299 countsByYear W32023752992021 @default.
- W3202375299 countsByYear W32023752992023 @default.
- W3202375299 crossrefType "book-chapter" @default.
- W3202375299 hasAuthorship W3202375299A5023086649 @default.
- W3202375299 hasAuthorship W3202375299A5024258334 @default.
- W3202375299 hasAuthorship W3202375299A5052124868 @default.
- W3202375299 hasAuthorship W3202375299A5053905081 @default.
- W3202375299 hasAuthorship W3202375299A5071773009 @default.
- W3202375299 hasBestOaLocation W32023752992 @default.
- W3202375299 hasConcept C108583219 @default.
- W3202375299 hasConcept C119857082 @default.
- W3202375299 hasConcept C132525143 @default.
- W3202375299 hasConcept C138885662 @default.
- W3202375299 hasConcept C153180895 @default.
- W3202375299 hasConcept C154945302 @default.
- W3202375299 hasConcept C162324750 @default.
- W3202375299 hasConcept C187736073 @default.
- W3202375299 hasConcept C2776401178 @default.
- W3202375299 hasConcept C2780451532 @default.
- W3202375299 hasConcept C2984842247 @default.
- W3202375299 hasConcept C41008148 @default.
- W3202375299 hasConcept C41895202 @default.
- W3202375299 hasConcept C50644808 @default.
- W3202375299 hasConcept C80444323 @default.
- W3202375299 hasConceptScore W3202375299C108583219 @default.
- W3202375299 hasConceptScore W3202375299C119857082 @default.
- W3202375299 hasConceptScore W3202375299C132525143 @default.
- W3202375299 hasConceptScore W3202375299C138885662 @default.
- W3202375299 hasConceptScore W3202375299C153180895 @default.
- W3202375299 hasConceptScore W3202375299C154945302 @default.
- W3202375299 hasConceptScore W3202375299C162324750 @default.
- W3202375299 hasConceptScore W3202375299C187736073 @default.
- W3202375299 hasConceptScore W3202375299C2776401178 @default.
- W3202375299 hasConceptScore W3202375299C2780451532 @default.
- W3202375299 hasConceptScore W3202375299C2984842247 @default.
- W3202375299 hasConceptScore W3202375299C41008148 @default.
- W3202375299 hasConceptScore W3202375299C41895202 @default.
- W3202375299 hasConceptScore W3202375299C50644808 @default.
- W3202375299 hasConceptScore W3202375299C80444323 @default.
- W3202375299 hasLocation W32023752991 @default.
- W3202375299 hasLocation W32023752992 @default.
- W3202375299 hasOpenAccess W3202375299 @default.
- W3202375299 hasPrimaryLocation W32023752991 @default.
- W3202375299 hasRelatedWork W2773120646 @default.
- W3202375299 hasRelatedWork W2909645158 @default.
- W3202375299 hasRelatedWork W2950066684 @default.
- W3202375299 hasRelatedWork W3082895349 @default.
- W3202375299 hasRelatedWork W3162132941 @default.
- W3202375299 hasRelatedWork W3179488938 @default.
- W3202375299 hasRelatedWork W4288853838 @default.
- W3202375299 hasRelatedWork W4298388782 @default.
- W3202375299 hasRelatedWork W4312831135 @default.
- W3202375299 hasRelatedWork W4318819771 @default.
- W3202375299 isParatext "false" @default.
- W3202375299 isRetracted "false" @default.
- W3202375299 magId "3202375299" @default.
- W3202375299 workType "book-chapter" @default.