FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318823333> ?p ?o ?g. }

• W4318823333 abstract "Structured sequences are a popular data representation, used to model complex data such as traffic networks. A key machine learning task for structured sequences is node classification, that is predicting the class labels of unlabeled nodes. Though many node classification models were proposed, they assume a closed world setting, that all class labels appear in the training data. But in the real-world, the presence of never-before-seen class labels in testing data can considerably degrade a classifier’s accuracy. A promising solution to this issue is to build classifiers for an open-world setting, where samples with unknown class labels are continuously observed such that training and testing data may have different class label spaces. Several approaches have been proposed for open-world learning problems in computer vision and natural language processing, but they cannot be applied directly to structured sequences due to the complexity of their non-Euclidean properties and their dynamic nature. This paper addresses this important research gap by proposing a novel Open-world Structured Sequence node Classification (OSSC) model, to learn from structured sequences in an open-world setting. OSSC captures the structural and temporal information via a GCN-based dynamic variational framework. A latent distribution sequence is learned for each node using both stochastic states and deterministic states, to capture the evolution of node attributes and topology, followed by a sampling process to generate node representations. An open-world classification loss is further adopted to ensure that node representations are sensitive to unknown classes. And a combination of Openmax and Softmax is utilized to recognize nodes from unknown classes and to classify others to one of the known classes. Experiments on real-world datasets show that the proposed OSSC method is capable of learning accurate open-world node classifiers from structured sequence data." @default.
• W4318823333 created "2023-02-02" @default.
• W4318823333 creator A5003347359 @default.
• W4318823333 creator A5008056593 @default.
• W4318823333 creator A5029360035 @default.
• W4318823333 creator A5032148962 @default.
• W4318823333 creator A5051163908 @default.
• W4318823333 creator A5063127492 @default.
• W4318823333 creator A5066646399 @default.
• W4318823333 date "2022-11-01" @default.
• W4318823333 modified "2023-10-16" @default.
• W4318823333 title "A Dynamic Variational Framework for Open-World Node Classification in Structured Sequences" @default.
• W4318823333 cites W1982459859 @default.
• W4318823333 cites W2014679376 @default.
• W4318823333 cites W2890659396 @default.
• W4318823333 cites W2950969150 @default.
• W4318823333 cites W2963149653 @default.
• W4318823333 cites W2963212338 @default.
• W4318823333 cites W2963875483 @default.
• W4318823333 cites W2963924212 @default.
• W4318823333 cites W2964811671 @default.
• W4318823333 cites W2971624117 @default.
• W4318823333 cites W2997848713 @default.
• W4318823333 cites W2998116985 @default.
• W4318823333 cites W2998313947 @default.
• W4318823333 cites W3004366655 @default.
• W4318823333 cites W3014773921 @default.
• W4318823333 cites W3035081753 @default.
• W4318823333 cites W3035224069 @default.
• W4318823333 cites W3035371495 @default.
• W4318823333 cites W3045255111 @default.
• W4318823333 cites W3109137304 @default.
• W4318823333 cites W3112926360 @default.
• W4318823333 cites W3113256917 @default.
• W4318823333 cites W3128465814 @default.
• W4318823333 cites W3129488702 @default.
• W4318823333 cites W3136640655 @default.
• W4318823333 cites W3173421061 @default.
• W4318823333 cites W3176709420 @default.
• W4318823333 cites W3189989129 @default.
• W4318823333 cites W3191599629 @default.
• W4318823333 cites W3199066198 @default.
• W4318823333 cites W3199378187 @default.
• W4318823333 doi "https://doi.org/10.1109/icdm54844.2022.00081" @default.
• W4318823333 hasPublicationYear "2022" @default.
• W4318823333 type Work @default.
• W4318823333 citedByCount "1" @default.
• W4318823333 countsByYear W43188233332023 @default.
• W4318823333 crossrefType "proceedings-article" @default.
• W4318823333 hasAuthorship W4318823333A5003347359 @default.
• W4318823333 hasAuthorship W4318823333A5008056593 @default.
• W4318823333 hasAuthorship W4318823333A5029360035 @default.
• W4318823333 hasAuthorship W4318823333A5032148962 @default.
• W4318823333 hasAuthorship W4318823333A5051163908 @default.
• W4318823333 hasAuthorship W4318823333A5063127492 @default.
• W4318823333 hasAuthorship W4318823333A5066646399 @default.
• W4318823333 hasConcept C119857082 @default.
• W4318823333 hasConcept C124101348 @default.
• W4318823333 hasConcept C127413603 @default.
• W4318823333 hasConcept C154945302 @default.
• W4318823333 hasConcept C162324750 @default.
• W4318823333 hasConcept C187736073 @default.
• W4318823333 hasConcept C2777212361 @default.
• W4318823333 hasConcept C2780451532 @default.
• W4318823333 hasConcept C35639132 @default.
• W4318823333 hasConcept C41008148 @default.
• W4318823333 hasConcept C62611344 @default.
• W4318823333 hasConcept C66938386 @default.
• W4318823333 hasConcept C80444323 @default.
• W4318823333 hasConcept C95623464 @default.
• W4318823333 hasConceptScore W4318823333C119857082 @default.
• W4318823333 hasConceptScore W4318823333C124101348 @default.
• W4318823333 hasConceptScore W4318823333C127413603 @default.
• W4318823333 hasConceptScore W4318823333C154945302 @default.
• W4318823333 hasConceptScore W4318823333C162324750 @default.
• W4318823333 hasConceptScore W4318823333C187736073 @default.
• W4318823333 hasConceptScore W4318823333C2777212361 @default.
• W4318823333 hasConceptScore W4318823333C2780451532 @default.
• W4318823333 hasConceptScore W4318823333C35639132 @default.
• W4318823333 hasConceptScore W4318823333C41008148 @default.
• W4318823333 hasConceptScore W4318823333C62611344 @default.
• W4318823333 hasConceptScore W4318823333C66938386 @default.
• W4318823333 hasConceptScore W4318823333C80444323 @default.
• W4318823333 hasConceptScore W4318823333C95623464 @default.
• W4318823333 hasFunder F4320330400 @default.
• W4318823333 hasLocation W43188233331 @default.
• W4318823333 hasOpenAccess W4318823333 @default.
• W4318823333 hasPrimaryLocation W43188233331 @default.
• W4318823333 hasRelatedWork W2171095014 @default.
• W4318823333 hasRelatedWork W2512018286 @default.
• W4318823333 hasRelatedWork W2556319748 @default.
• W4318823333 hasRelatedWork W2891961174 @default.
• W4318823333 hasRelatedWork W2947903144 @default.
• W4318823333 hasRelatedWork W2961085424 @default.
• W4318823333 hasRelatedWork W3158264953 @default.
• W4318823333 hasRelatedWork W3200179079 @default.
• W4318823333 hasRelatedWork W4249229055 @default.
• W4318823333 hasRelatedWork W4310989423 @default.
• W4318823333 isParatext "false" @default.
• W4318823333 isRetracted "false" @default.

• next