Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226119078> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4226119078 abstract "Graph Neural Networks have become one of the indispensable tools to learn from graph-structured data, and their usefulness has been shown in wide variety of tasks. In recent years, there have been tremendous improvements in architecture design, resulting in better performance on various prediction tasks. In general, these neural architectures combine node feature aggregation and feature transformation using learnable weight matrix in the same layer. This makes it challenging to analyze the importance of node features aggregated from various hops and the expressiveness of the neural network layers. As different graph datasets show varying levels of homophily and heterophily in features and class label distribution, it becomes essential to understand which features are important for the prediction tasks without any prior information. In this work, we decouple the node feature aggregation step and depth of graph neural network, and empirically analyze how different aggregated features play a role in prediction performance. We show that not all features generated via aggregation steps are useful, and often using these less informative features can be detrimental to the performance of the GNN model. Through our experiments, we show that learning certain subsets of these features can lead to better performance on wide variety of datasets. We propose to use softmax as a regularizer and soft-selector of features aggregated from neighbors at different hop distances; and L2-Normalization over GNN layers. Combining these techniques, we present a simple and shallow model, Feature Selection Graph Neural Network (FSGNN), and show empirically that the proposed model achieves comparable or even higher accuracy than state-of-the-art GNN models in nine benchmark datasets for the node classification task, with remarkable improvements up to 51.1%." @default.
- W4226119078 created "2022-05-05" @default.
- W4226119078 creator A5021687717 @default.
- W4226119078 creator A5064265813 @default.
- W4226119078 creator A5076510932 @default.
- W4226119078 date "2021-11-12" @default.
- W4226119078 modified "2023-09-23" @default.
- W4226119078 title "Simplifying approach to Node Classification in Graph Neural Networks" @default.
- W4226119078 hasPublicationYear "2021" @default.
- W4226119078 type Work @default.
- W4226119078 citedByCount "0" @default.
- W4226119078 crossrefType "posted-content" @default.
- W4226119078 hasAuthorship W4226119078A5021687717 @default.
- W4226119078 hasAuthorship W4226119078A5064265813 @default.
- W4226119078 hasAuthorship W4226119078A5076510932 @default.
- W4226119078 hasBestOaLocation W42261190781 @default.
- W4226119078 hasConcept C114614502 @default.
- W4226119078 hasConcept C119857082 @default.
- W4226119078 hasConcept C124101348 @default.
- W4226119078 hasConcept C132525143 @default.
- W4226119078 hasConcept C136886441 @default.
- W4226119078 hasConcept C138885662 @default.
- W4226119078 hasConcept C144024400 @default.
- W4226119078 hasConcept C148483581 @default.
- W4226119078 hasConcept C153180895 @default.
- W4226119078 hasConcept C154945302 @default.
- W4226119078 hasConcept C188441871 @default.
- W4226119078 hasConcept C19165224 @default.
- W4226119078 hasConcept C2776401178 @default.
- W4226119078 hasConcept C2779812341 @default.
- W4226119078 hasConcept C33923547 @default.
- W4226119078 hasConcept C41008148 @default.
- W4226119078 hasConcept C41895202 @default.
- W4226119078 hasConcept C50644808 @default.
- W4226119078 hasConcept C80444323 @default.
- W4226119078 hasConceptScore W4226119078C114614502 @default.
- W4226119078 hasConceptScore W4226119078C119857082 @default.
- W4226119078 hasConceptScore W4226119078C124101348 @default.
- W4226119078 hasConceptScore W4226119078C132525143 @default.
- W4226119078 hasConceptScore W4226119078C136886441 @default.
- W4226119078 hasConceptScore W4226119078C138885662 @default.
- W4226119078 hasConceptScore W4226119078C144024400 @default.
- W4226119078 hasConceptScore W4226119078C148483581 @default.
- W4226119078 hasConceptScore W4226119078C153180895 @default.
- W4226119078 hasConceptScore W4226119078C154945302 @default.
- W4226119078 hasConceptScore W4226119078C188441871 @default.
- W4226119078 hasConceptScore W4226119078C19165224 @default.
- W4226119078 hasConceptScore W4226119078C2776401178 @default.
- W4226119078 hasConceptScore W4226119078C2779812341 @default.
- W4226119078 hasConceptScore W4226119078C33923547 @default.
- W4226119078 hasConceptScore W4226119078C41008148 @default.
- W4226119078 hasConceptScore W4226119078C41895202 @default.
- W4226119078 hasConceptScore W4226119078C50644808 @default.
- W4226119078 hasConceptScore W4226119078C80444323 @default.
- W4226119078 hasLocation W42261190781 @default.
- W4226119078 hasOpenAccess W4226119078 @default.
- W4226119078 hasPrimaryLocation W42261190781 @default.
- W4226119078 hasRelatedWork W11389402 @default.
- W4226119078 hasRelatedWork W12546350 @default.
- W4226119078 hasRelatedWork W12783365 @default.
- W4226119078 hasRelatedWork W12820539 @default.
- W4226119078 hasRelatedWork W13109368 @default.
- W4226119078 hasRelatedWork W13426584 @default.
- W4226119078 hasRelatedWork W17411213 @default.
- W4226119078 hasRelatedWork W4061672 @default.
- W4226119078 hasRelatedWork W7066080 @default.
- W4226119078 hasRelatedWork W8787759 @default.
- W4226119078 hasRelatedWork W9448574 @default.
- W4226119078 hasRelatedWork W16836940 @default.
- W4226119078 hasRelatedWork W855484 @default.
- W4226119078 isParatext "false" @default.
- W4226119078 isRetracted "false" @default.
- W4226119078 workType "article" @default.