FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281263494> ?p ?o ?g. }

• W4281263494 endingPage "15" @default.
• W4281263494 startingPage "1" @default.
• W4281263494 abstract "Graph classification plays an important role in a wide range of applications from biological prediction to social analysis. Traditional graph classification models built on graph kernels are hampered by the challenge of poor generalization as they are heavily dependent on the dedicated design of handcrafted features. Recently, graph neural networks (GNNs) become a new class of tools for analyzing graph data and have achieved promising performance. However, it is necessary to collect a large number of labeled graph data for training an accurate GNN, which is often unaffordable in real-world applications. Therefore, it is an open question to build GNNs under the condition of few-shot learning where only a few labeled graphs are available. In this article, we introduce a new Structure-aware Prototypical Neural Process (SPNP for short) for a few-shot graph classification. Specifically, at the encoding stage, SPNP first employs GNNs to capture graph structure information. Then, SPNP incorporates such structural priors into the latent path and the deterministic path for representing stochastic processes. At the decoding stage, SPNP uses a new prototypical decoder to define a metric space where unseen graphs can be predicted effectively. The proposed decoder, which contains a self-attention mechanism to learn the intraclass dependence between graphs, can enhance the class-level representations, especially for new classes. Furthermore, benefited from such a flexible encoding-decoding architecture, SPNP can directly map the context samples to a predictive distribution without any complicated operations used in previous methods. Extensive experiments demonstrate that SPNP achieves consistent and significant improvements over state-of-the-art methods. Further discussions are provided toward model efficiency and more detailed analysis." @default.
• W4281263494 created "2022-05-23" @default.
• W4281263494 creator A5029360035 @default.
• W4281263494 creator A5035738011 @default.
• W4281263494 creator A5054247612 @default.
• W4281263494 creator A5056608045 @default.
• W4281263494 creator A5074524814 @default.
• W4281263494 creator A5085319576 @default.
• W4281263494 creator A5089580618 @default.
• W4281263494 date "2022-01-01" @default.
• W4281263494 modified "2023-10-17" @default.
• W4281263494 title "Structure-Aware Prototypical Neural Process for Few-Shot Graph Classification" @default.
• W4281263494 doi "https://doi.org/10.1109/tnnls.2022.3173318" @default.
• W4281263494 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35594237" @default.
• W4281263494 hasPublicationYear "2022" @default.
• W4281263494 type Work @default.
• W4281263494 citedByCount "2" @default.
• W4281263494 countsByYear W42812634942023 @default.
• W4281263494 crossrefType "journal-article" @default.
• W4281263494 hasAuthorship W4281263494A5029360035 @default.
• W4281263494 hasAuthorship W4281263494A5035738011 @default.
• W4281263494 hasAuthorship W4281263494A5054247612 @default.
• W4281263494 hasAuthorship W4281263494A5056608045 @default.
• W4281263494 hasAuthorship W4281263494A5074524814 @default.
• W4281263494 hasAuthorship W4281263494A5085319576 @default.
• W4281263494 hasAuthorship W4281263494A5089580618 @default.
• W4281263494 hasConcept C11413529 @default.
• W4281263494 hasConcept C119857082 @default.
• W4281263494 hasConcept C124101348 @default.
• W4281263494 hasConcept C132525143 @default.
• W4281263494 hasConcept C154945302 @default.
• W4281263494 hasConcept C41008148 @default.
• W4281263494 hasConcept C57273362 @default.
• W4281263494 hasConcept C80444323 @default.
• W4281263494 hasConceptScore W4281263494C11413529 @default.
• W4281263494 hasConceptScore W4281263494C119857082 @default.
• W4281263494 hasConceptScore W4281263494C124101348 @default.
• W4281263494 hasConceptScore W4281263494C132525143 @default.
• W4281263494 hasConceptScore W4281263494C154945302 @default.
• W4281263494 hasConceptScore W4281263494C41008148 @default.
• W4281263494 hasConceptScore W4281263494C57273362 @default.
• W4281263494 hasConceptScore W4281263494C80444323 @default.
• W4281263494 hasFunder F4320321001 @default.
• W4281263494 hasLocation W42812634941 @default.
• W4281263494 hasLocation W42812634942 @default.
• W4281263494 hasOpenAccess W4281263494 @default.
• W4281263494 hasPrimaryLocation W42812634941 @default.
• W4281263494 hasRelatedWork W2030492936 @default.
• W4281263494 hasRelatedWork W2351992004 @default.
• W4281263494 hasRelatedWork W2358034992 @default.
• W4281263494 hasRelatedWork W2380207131 @default.
• W4281263494 hasRelatedWork W2383319832 @default.
• W4281263494 hasRelatedWork W2961085424 @default.
• W4281263494 hasRelatedWork W4286629047 @default.
• W4281263494 hasRelatedWork W4306321456 @default.
• W4281263494 hasRelatedWork W4306674287 @default.
• W4281263494 hasRelatedWork W4224009465 @default.
• W4281263494 isParatext "false" @default.
• W4281263494 isRetracted "false" @default.
• W4281263494 workType "article" @default.