ScaleGCN: Efficient and Effective Graph Convolution via Channel-Wise Scale Transformation.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3199390
Abstract: Graph convolutional networks (GCNs) have shown success in many graph-based applications as they can combine node features and graph topology to obtain expressive embeddings. While there exist numerous GCN variants, a typical graph convolution layer… read more here.
Keywords: channel wise; wise scale; graph convolution; scale transformation ... See more keywords