Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313253604> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4313253604 endingPage "480" @default.
- W4313253604 startingPage "469" @default.
- W4313253604 abstract "Graph neural network is a breakthrough in applying deep learning to non-Euclidean space. It is widely used for tasks such as social network analysis, molecular function inference, drug repositioning and protein modeling, achieving outstanding performance on relational models. Despite the great success of graph neural networks, most of them cannot be generalized to various scenarios. This is because graph information needs variation for different tasks and fixed models limit the flexibility of feature extraction. To address this challenge, we design a graph filter that can be adaptively adjusted according to graph tasks. This filter combines the multi-view strategy with the learnable quadratic frequency response function, using the crests of the quadratic functions to adaptively emphasize the required information. We further design the graph convolutional network model base on this adaptive filter, named AF-GCN. Extensive experiments are performed with 13 SOTA models on 12 different real-world datasets, including homogeneous and heterogeneous datasets in the node classification task, biological datasets, and social network datasets in the graph classification task. AF-GCN achieves state-of-the-art results in various scenarios. In addition, AF-GCN has high interpretability in the graph spatial domain. The development process from Graph Convolutional Networks (GCN) to AF-GCN has historical similarities with the development of Convolution Neural Networks (CNN)." @default.
- W4313253604 created "2023-01-06" @default.
- W4313253604 creator A5002188808 @default.
- W4313253604 creator A5013235521 @default.
- W4313253604 creator A5013544266 @default.
- W4313253604 creator A5019999723 @default.
- W4313253604 creator A5021584178 @default.
- W4313253604 creator A5045673750 @default.
- W4313253604 creator A5050438640 @default.
- W4313253604 creator A5084210456 @default.
- W4313253604 date "2023-04-01" @default.
- W4313253604 modified "2023-10-06" @default.
- W4313253604 title "AF-GCN: Completing various graph tasks efficiently via adaptive quadratic frequency response function in graph spectral domain" @default.
- W4313253604 cites W1977317053 @default.
- W4313253604 cites W2092750499 @default.
- W4313253604 cites W2099438806 @default.
- W4313253604 cites W2101491865 @default.
- W4313253604 cites W2116341502 @default.
- W4313253604 cites W2788919350 @default.
- W4313253604 cites W2966859223 @default.
- W4313253604 cites W2992752586 @default.
- W4313253604 cites W3044334750 @default.
- W4313253604 cites W3105259638 @default.
- W4313253604 cites W3128443161 @default.
- W4313253604 cites W4210257598 @default.
- W4313253604 cites W4224884326 @default.
- W4313253604 cites W4297121106 @default.
- W4313253604 doi "https://doi.org/10.1016/j.ins.2022.12.054" @default.
- W4313253604 hasPublicationYear "2023" @default.
- W4313253604 type Work @default.
- W4313253604 citedByCount "2" @default.
- W4313253604 countsByYear W43132536042023 @default.
- W4313253604 crossrefType "journal-article" @default.
- W4313253604 hasAuthorship W4313253604A5002188808 @default.
- W4313253604 hasAuthorship W4313253604A5013235521 @default.
- W4313253604 hasAuthorship W4313253604A5013544266 @default.
- W4313253604 hasAuthorship W4313253604A5019999723 @default.
- W4313253604 hasAuthorship W4313253604A5021584178 @default.
- W4313253604 hasAuthorship W4313253604A5045673750 @default.
- W4313253604 hasAuthorship W4313253604A5050438640 @default.
- W4313253604 hasAuthorship W4313253604A5084210456 @default.
- W4313253604 hasConcept C11413529 @default.
- W4313253604 hasConcept C132525143 @default.
- W4313253604 hasConcept C153180895 @default.
- W4313253604 hasConcept C154945302 @default.
- W4313253604 hasConcept C2776214188 @default.
- W4313253604 hasConcept C2781067378 @default.
- W4313253604 hasConcept C41008148 @default.
- W4313253604 hasConcept C80444323 @default.
- W4313253604 hasConceptScore W4313253604C11413529 @default.
- W4313253604 hasConceptScore W4313253604C132525143 @default.
- W4313253604 hasConceptScore W4313253604C153180895 @default.
- W4313253604 hasConceptScore W4313253604C154945302 @default.
- W4313253604 hasConceptScore W4313253604C2776214188 @default.
- W4313253604 hasConceptScore W4313253604C2781067378 @default.
- W4313253604 hasConceptScore W4313253604C41008148 @default.
- W4313253604 hasConceptScore W4313253604C80444323 @default.
- W4313253604 hasLocation W43132536041 @default.
- W4313253604 hasOpenAccess W4313253604 @default.
- W4313253604 hasPrimaryLocation W43132536041 @default.
- W4313253604 hasRelatedWork W2355108509 @default.
- W4313253604 hasRelatedWork W2470825435 @default.
- W4313253604 hasRelatedWork W2951515642 @default.
- W4313253604 hasRelatedWork W2979535968 @default.
- W4313253604 hasRelatedWork W3168657718 @default.
- W4313253604 hasRelatedWork W3202522988 @default.
- W4313253604 hasRelatedWork W3204410986 @default.
- W4313253604 hasRelatedWork W4221015625 @default.
- W4313253604 hasRelatedWork W4304700924 @default.
- W4313253604 hasRelatedWork W4377247618 @default.
- W4313253604 hasVolume "623" @default.
- W4313253604 isParatext "false" @default.
- W4313253604 isRetracted "false" @default.
- W4313253604 workType "article" @default.