Graph Neural Networks with Diverse Spectral Filtering

arXiv:2312.09041v2 Announce Type: replace
Abstract: Spectral Graph Neural Networks (GNNs) have achieved tremendous success in graph machine learning, with polynomial filters applied for graph convolutions, where all nodes share the identical filter weights to mine their local contexts. Despite the success, existing spectral GNNs usually fail to deal with complex networks (e.g., WWW) due to such homogeneous spectral filtering setting that ignores the regional heterogeneity as typically seen in real-world networks. To tackle this issue, we propose a novel diverse …

arxiv cs.lg cs.si diverse filtering graph graph neural networks networks neural networks type