FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3045020488> ?p ?o ?g. }

• W3045020488 abstract "Graph Neural Networks (GNNs) have recently caught great attention and achieved significant progress in graph-level applications. In order to handle graphs with different features and sizes, we propose a novel graph neural network, which we call HaarNet, to predict graph labels with interrelated convolution and pooling strategies. Similar to some existing routines, the model assembles unified graph-level representations from samples by first adopting graph convolutional layers to extract mutual information followed by graph pooling layers to downsample graph resolution. By a sequence of clusterings, we embed the intrinsic topological information of each graph into the GNN. Through the fast Haar transformation, we made our contribution to forming a smooth workflow that learns multi-scale graph representation with redundancy removed. As a result, our proposed framework obtains notable accuracy gains without sacrificing performance stability. Extensive experiments validate the superiority on graph classification and regression tasks, where our proposed HaarNet outperforms various existing GNN models, especially on big data sets." @default.
• W3045020488 created "2020-07-29" @default.
• W3045020488 creator A5015817857 @default.
• W3045020488 creator A5019662747 @default.
• W3045020488 creator A5021384155 @default.
• W3045020488 creator A5027695625 @default.
• W3045020488 creator A5070236689 @default.
• W3045020488 date "2020-07-22" @default.
• W3045020488 modified "2023-09-24" @default.
• W3045020488 title "Graph Neural Networks with Haar Transform-Based Convolution and Pooling: A Complete Guide." @default.
• W3045020488 cites W1482568066 @default.
• W3045020488 cites W1501856433 @default.
• W3045020488 cites W1578099820 @default.
• W3045020488 cites W1738019091 @default.
• W3045020488 cites W1904365287 @default.
• W3045020488 cites W1968434397 @default.
• W3045020488 cites W2010793745 @default.
• W3045020488 cites W2056562706 @default.
• W3045020488 cites W2070232376 @default.
• W3045020488 cites W2092750499 @default.
• W3045020488 cites W2099438806 @default.
• W3045020488 cites W2101491865 @default.
• W3045020488 cites W2104489082 @default.
• W3045020488 cites W2113207845 @default.
• W3045020488 cites W2116341502 @default.
• W3045020488 cites W2119821739 @default.
• W3045020488 cites W2121947440 @default.
• W3045020488 cites W2127917465 @default.
• W3045020488 cites W2135674549 @default.
• W3045020488 cites W2139906443 @default.
• W3045020488 cites W2142498761 @default.
• W3045020488 cites W2144000913 @default.
• W3045020488 cites W2150120952 @default.
• W3045020488 cites W2150593711 @default.
• W3045020488 cites W2153693853 @default.
• W3045020488 cites W2159156271 @default.
• W3045020488 cites W2406128552 @default.
• W3045020488 cites W2558748708 @default.
• W3045020488 cites W2565684601 @default.
• W3045020488 cites W2594183968 @default.
• W3045020488 cites W2624431344 @default.
• W3045020488 cites W2771949901 @default.
• W3045020488 cites W2777802649 @default.
• W3045020488 cites W2788512147 @default.
• W3045020488 cites W2788919350 @default.
• W3045020488 cites W2805516822 @default.
• W3045020488 cites W2811124557 @default.
• W3045020488 cites W2883265831 @default.
• W3045020488 cites W2900470550 @default.
• W3045020488 cites W2905224888 @default.
• W3045020488 cites W2907620438 @default.
• W3045020488 cites W2911964244 @default.
• W3045020488 cites W2941859709 @default.
• W3045020488 cites W2947030669 @default.
• W3045020488 cites W2949117887 @default.
• W3045020488 cites W2962711740 @default.
• W3045020488 cites W2962779575 @default.
• W3045020488 cites W2963066159 @default.
• W3045020488 cites W2963175980 @default.
• W3045020488 cites W2963460103 @default.
• W3045020488 cites W2963464736 @default.
• W3045020488 cites W2963858333 @default.
• W3045020488 cites W2963984147 @default.
• W3045020488 cites W2964121744 @default.
• W3045020488 cites W2964311892 @default.
• W3045020488 cites W2964321699 @default.
• W3045020488 cites W2970971581 @default.
• W3045020488 cites W2973125186 @default.
• W3045020488 cites W2973511309 @default.
• W3045020488 cites W2979750740 @default.
• W3045020488 cites W2992345245 @default.
• W3045020488 cites W3007332492 @default.
• W3045020488 cites W3011667710 @default.
• W3045020488 cites W3021853564 @default.
• W3045020488 cites W3034679267 @default.
• W3045020488 cites W3035175601 @default.
• W3045020488 cites W3037338873 @default.
• W3045020488 cites W3090789587 @default.
• W3045020488 cites W3102337567 @default.
• W3045020488 cites W3104097132 @default.
• W3045020488 cites W3111965349 @default.
• W3045020488 cites W3021975806 @default.
• W3045020488 hasPublicationYear "2020" @default.
• W3045020488 type Work @default.
• W3045020488 sameAs 3045020488 @default.
• W3045020488 citedByCount "4" @default.
• W3045020488 countsByYear W30450204882020 @default.
• W3045020488 countsByYear W30450204882021 @default.
• W3045020488 countsByYear W30450204882023 @default.
• W3045020488 crossrefType "posted-content" @default.
• W3045020488 hasAuthorship W3045020488A5015817857 @default.
• W3045020488 hasAuthorship W3045020488A5019662747 @default.
• W3045020488 hasAuthorship W3045020488A5021384155 @default.
• W3045020488 hasAuthorship W3045020488A5027695625 @default.
• W3045020488 hasAuthorship W3045020488A5070236689 @default.
• W3045020488 hasConcept C11413529 @default.
• W3045020488 hasConcept C132525143 @default.
• W3045020488 hasConcept C153180895 @default.
• W3045020488 hasConcept C154945302 @default.
• W3045020488 hasConcept C41008148 @default.

• next