Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387521354> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4387521354 endingPage "10" @default.
- W4387521354 startingPage "1" @default.
- W4387521354 abstract "Graph Neural Networks (GNNs) have emerged as a crucial deep learning framework for graph-structured data. However, existing GNNs suffer from the scalability limitation, which hinders their practical implementation in industrial settings. Many scalable GNNs have been proposed to address this limitation. However, they have been proven to act as low-pass graph filters, which discard the valuable middle- and high-frequency information. This paper proposes a novel graph neural network named Adaptive Filtering Graph Neural Networks (AFGNN), which can capture all frequency information on large-scale graphs. AFGNN consists of two stages. The first stage utilizes low-, middle-, and high-pass graph filters to extract comprehensive frequency information without introducing additional parameters. This computation is a one-time task and is pre-computed before training, ensuring its scalability. The second stage incorporates a node-level attention-based feature combination, enabling the generation of customized graph filters for each node, contrary to existing spectral GNNs that employ uniform graph filters for the entire graph. AFGNN is suitable for mini-batch training, and can enhance scalability and efficiently capture all frequency information from large-scale graphs. We evaluate AFGNN by comparing its ability to capture all frequency information with spectral GNNs, and its scalability with scalable GNNs. Experimental results illustrate that AFGNN surpasses both scalable GNNs and spectral GNNs, highlighting its superiority." @default.
- W4387521354 created "2023-10-12" @default.
- W4387521354 creator A5015817857 @default.
- W4387521354 creator A5031436368 @default.
- W4387521354 creator A5050137000 @default.
- W4387521354 creator A5082380547 @default.
- W4387521354 creator A5083450478 @default.
- W4387521354 creator A5091751192 @default.
- W4387521354 date "2024-01-01" @default.
- W4387521354 modified "2023-10-18" @default.
- W4387521354 title "Beyond low-pass filtering on large-scale graphs via Adaptive Filtering Graph Neural Networks" @default.
- W4387521354 cites W1698699930 @default.
- W4387521354 cites W2101491865 @default.
- W4387521354 cites W2153959628 @default.
- W4387521354 cites W2161763921 @default.
- W4387521354 cites W2892880750 @default.
- W4387521354 cites W2972209102 @default.
- W4387521354 cites W3002924435 @default.
- W4387521354 cites W3011667710 @default.
- W4387521354 cites W3039500550 @default.
- W4387521354 cites W3166215705 @default.
- W4387521354 cites W3193670021 @default.
- W4387521354 cites W3215122682 @default.
- W4387521354 cites W4300961520 @default.
- W4387521354 cites W4308237904 @default.
- W4387521354 cites W4310255432 @default.
- W4387521354 cites W4323928697 @default.
- W4387521354 cites W4372266940 @default.
- W4387521354 doi "https://doi.org/10.1016/j.neunet.2023.09.042" @default.
- W4387521354 hasPublicationYear "2024" @default.
- W4387521354 type Work @default.
- W4387521354 citedByCount "0" @default.
- W4387521354 crossrefType "journal-article" @default.
- W4387521354 hasAuthorship W4387521354A5015817857 @default.
- W4387521354 hasAuthorship W4387521354A5031436368 @default.
- W4387521354 hasAuthorship W4387521354A5050137000 @default.
- W4387521354 hasAuthorship W4387521354A5082380547 @default.
- W4387521354 hasAuthorship W4387521354A5083450478 @default.
- W4387521354 hasAuthorship W4387521354A5091751192 @default.
- W4387521354 hasConcept C132525143 @default.
- W4387521354 hasConcept C154945302 @default.
- W4387521354 hasConcept C41008148 @default.
- W4387521354 hasConcept C48044578 @default.
- W4387521354 hasConcept C50644808 @default.
- W4387521354 hasConcept C77088390 @default.
- W4387521354 hasConcept C80444323 @default.
- W4387521354 hasConceptScore W4387521354C132525143 @default.
- W4387521354 hasConceptScore W4387521354C154945302 @default.
- W4387521354 hasConceptScore W4387521354C41008148 @default.
- W4387521354 hasConceptScore W4387521354C48044578 @default.
- W4387521354 hasConceptScore W4387521354C50644808 @default.
- W4387521354 hasConceptScore W4387521354C77088390 @default.
- W4387521354 hasConceptScore W4387521354C80444323 @default.
- W4387521354 hasLocation W43875213541 @default.
- W4387521354 hasOpenAccess W4387521354 @default.
- W4387521354 hasPrimaryLocation W43875213541 @default.
- W4387521354 hasRelatedWork W1838576100 @default.
- W4387521354 hasRelatedWork W1983399550 @default.
- W4387521354 hasRelatedWork W2089704382 @default.
- W4387521354 hasRelatedWork W2095886385 @default.
- W4387521354 hasRelatedWork W2357523926 @default.
- W4387521354 hasRelatedWork W2389214306 @default.
- W4387521354 hasRelatedWork W2889616422 @default.
- W4387521354 hasRelatedWork W2965083567 @default.
- W4387521354 hasRelatedWork W4235240664 @default.
- W4387521354 hasRelatedWork W97075385 @default.
- W4387521354 hasVolume "169" @default.
- W4387521354 isParatext "false" @default.
- W4387521354 isRetracted "false" @default.
- W4387521354 workType "article" @default.