Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210257598> ?p ?o ?g. }
- W4210257598 endingPage "24" @default.
- W4210257598 startingPage "4" @default.
- W4210257598 abstract "Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications, where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial-temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field." @default.
- W4210257598 created "2022-02-08" @default.
- W4210257598 creator A5008056593 @default.
- W4210257598 creator A5028402625 @default.
- W4210257598 creator A5036357902 @default.
- W4210257598 creator A5059227406 @default.
- W4210257598 creator A5074852078 @default.
- W4210257598 creator A5083854216 @default.
- W4210257598 date "2021-01-01" @default.
- W4210257598 modified "2023-10-13" @default.
- W4210257598 title "A Comprehensive Survey on Graph Neural Networks" @default.
- W4210257598 cites W1501856433 @default.
- W4210257598 cites W1512387364 @default.
- W4210257598 cites W1902237438 @default.
- W4210257598 cites W1991252559 @default.
- W4210257598 cites W2000375074 @default.
- W4210257598 cites W2022322548 @default.
- W4210257598 cites W2025768430 @default.
- W4210257598 cites W2046253692 @default.
- W4210257598 cites W2056562706 @default.
- W4210257598 cites W2064675550 @default.
- W4210257598 cites W2080731889 @default.
- W4210257598 cites W2092750499 @default.
- W4210257598 cites W2099438806 @default.
- W4210257598 cites W2101491865 @default.
- W4210257598 cites W2112796928 @default.
- W4210257598 cites W2116341502 @default.
- W4210257598 cites W2121406124 @default.
- W4210257598 cites W2135957668 @default.
- W4210257598 cites W2137983211 @default.
- W4210257598 cites W2139906443 @default.
- W4210257598 cites W2150120952 @default.
- W4210257598 cites W2151827881 @default.
- W4210257598 cites W2153513200 @default.
- W4210257598 cites W2153959628 @default.
- W4210257598 cites W2157331557 @default.
- W4210257598 cites W2160815625 @default.
- W4210257598 cites W2161763921 @default.
- W4210257598 cites W2166681504 @default.
- W4210257598 cites W2194775991 @default.
- W4210257598 cites W2258064579 @default.
- W4210257598 cites W2290847742 @default.
- W4210257598 cites W2343790552 @default.
- W4210257598 cites W2393319904 @default.
- W4210257598 cites W2526511911 @default.
- W4210257598 cites W2527189750 @default.
- W4210257598 cites W2557074642 @default.
- W4210257598 cites W2558460151 @default.
- W4210257598 cites W2558748708 @default.
- W4210257598 cites W2579549467 @default.
- W4210257598 cites W2594083602 @default.
- W4210257598 cites W2600702321 @default.
- W4210257598 cites W2606202972 @default.
- W4210257598 cites W2612872092 @default.
- W4210257598 cites W2735272571 @default.
- W4210257598 cites W2767404761 @default.
- W4210257598 cites W2768308213 @default.
- W4210257598 cites W2776622059 @default.
- W4210257598 cites W2788284887 @default.
- W4210257598 cites W2798296074 @default.
- W4210257598 cites W2798749466 @default.
- W4210257598 cites W2808373708 @default.
- W4210257598 cites W2808409763 @default.
- W4210257598 cites W2808867307 @default.
- W4210257598 cites W2808987817 @default.
- W4210257598 cites W2809343047 @default.
- W4210257598 cites W2809583854 @default.
- W4210257598 cites W2887092413 @default.
- W4210257598 cites W2889399096 @default.
- W4210257598 cites W2903871660 @default.
- W4210257598 cites W2911286998 @default.
- W4210257598 cites W2914080035 @default.
- W4210257598 cites W2945827377 @default.
- W4210257598 cites W2962975498 @default.
- W4210257598 cites W2963021451 @default.
- W4210257598 cites W2963037989 @default.
- W4210257598 cites W2963084622 @default.
- W4210257598 cites W2963165299 @default.
- W4210257598 cites W2963184176 @default.
- W4210257598 cites W2963224980 @default.
- W4210257598 cites W2963280944 @default.
- W4210257598 cites W2963281829 @default.
- W4210257598 cites W2963312728 @default.
- W4210257598 cites W2963333168 @default.
- W4210257598 cites W2963374482 @default.
- W4210257598 cites W2963415211 @default.
- W4210257598 cites W2963512530 @default.
- W4210257598 cites W2963653811 @default.
- W4210257598 cites W2963964898 @default.
- W4210257598 cites W2964094751 @default.
- W4210257598 cites W2965341826 @default.
- W4210257598 cites W2965949912 @default.
- W4210257598 cites W2966149470 @default.
- W4210257598 cites W3098269892 @default.
- W4210257598 cites W3100848837 @default.
- W4210257598 cites W3103720336 @default.
- W4210257598 cites W3104097132 @default.
- W4210257598 cites W3105136071 @default.