When Spectral Domain Meets Spatial Domain in Graph Neural Networks
| Autor: | Muhammet, Balcilar, Guillaume, Renton, Pierre, Héroux, Benoit, Gaüzère, Sébastien, Adam, Honeine, Paul |
|---|---|
| Přispěvatelé: | Honeine, Paul, APPEL À PROJETS GÉNÉRIQUE 2018 - Apprivoiser la Pré-image - - APi2018 - ANR-18-CE23-0014 - AAPG2018 - VALID, Equipe Apprentissage (DocApp - LITIS), Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Normandie Université (NU), ANR-18-CE23-0014,APi,Apprivoiser la Pré-image(2018) |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI]
[INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing [INFO.INFO-NE] Computer Science [cs]/Neural and Evolutionary Computing [cs.NE] [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE] [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] [STAT.ML]Statistics [stat]/Machine Learning [stat.ML] [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [INFO.INFO-CY]Computer Science [cs]/Computers and Society [cs.CY] [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST] spatial domain [MATH.MATH-ST] Mathematics [math]/Statistics [math.ST] [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV] graph neural networks deep learning [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG] spectral analysis [STAT.ML] Statistics [stat]/Machine Learning [stat.ML] graph data [INFO.INFO-CY] Computer Science [cs]/Computers and Society [cs.CY] graph convolution networks Convolutional neural networks ChebNet CayleyNet graph attention networks spectral domain [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing eigenanalysis |
| Zdroj: | Thirty-seventh International Conference on Machine Learning (ICML 2020)-Workshop on Graph Representation Learning and Beyond (GRL+ 2020) Thirty-seventh International Conference on Machine Learning (ICML 2020)-Workshop on Graph Representation Learning and Beyond (GRL+ 2020), Jul 2020, Vienna, Austria |
| Popis: | International audience; Convolutional Graph Neural Networks (Con-vGNNs) are designed either in the spectral domain or in the spatial domain. In this paper, we provide a theoretical framework to analyze these neural networks, by deriving some equivalence of the graph convolution processes, regardless if they are designed in the spatial or the spectral domain. We demonstrate the relevance of the proposed framework by providing a spectral analysis of the most popular ConvGNNs (ChebNet, CayleyNet, GCN and Graph Attention Networks), which allows to explain their performance and shows their limits. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|