A Simple Yet Effective Framelet-Based Graph Neural Network for Directed Graphs
Chunya Zou, Andi Han, Lequan Lin, Ming Li, Junbin Gao
Abstract
In this work, we propose a spectral-based graph convolutional network for directed graphs. The proposed model employs the classic singular value decomposition (SVD) to perform signal decomposition directly on the asymmetric adjacency matrix. This strategy is simple, which allows many existing spectral-based methods to be adapted to directed graphs. We particularly utilize framelets-based filtering, which significantly enhances the learning capacity due to the separated modeling of information at different frequencies. We empirically observe the proposed model achieves the state-of-the-art results on various datasets. We also show that the model is robust to feature perturbation.
Topics & Concepts
Adjacency matrixSingular value decompositionComputer scienceSimple (philosophy)Directed graphAlgorithmGraphConvolutional neural networkMatrix decompositionModular decompositionFeature (linguistics)Artificial intelligenceTheoretical computer sciencePattern recognition (psychology)Line graphPathwidthEigenvalues and eigenvectorsEpistemologyQuantum mechanicsPhilosophyLinguisticsPhysicsAdvanced Graph Neural NetworksComplex Network Analysis TechniquesTopic Modeling