Multiview Deep Graph Infomax to Achieve Unsupervised Graph Embedding.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on cybernetics"
DOI: 10.1109/tcyb.2022.3163721
Abstract: Unsupervised graph embedding aims to extract highly discriminative node representations that facilitate the subsequent analysis. Converging evidence shows that a multiview graph provides a more comprehensive relationship between nodes than a single-view graph to capture… read more here.
Keywords: node representations; multiview deep; graph; unsupervised graph ... See more keywords
Learning Structural Node Representations Using Graph Kernels
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Knowledge and Data Engineering"
DOI: 10.1109/tkde.2019.2947478
Abstract: Many applications require identifying nodes that perform similar functions in a graph. For instance, identifying structurally equivalent nodes can provide insight into the structure of complex networks. Learning latent representations that capture such structural role… read more here.
Keywords: node representations; structural node; learning structural; using graph ... See more keywords
HGBER: Heterogeneous Graph Neural Network With Bidirectional Encoding Representation.
Sign Up to like & getrecommendations! Published in 2023 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3232709
Abstract: Heterogeneous graphs with multiple types of nodes and link relationships are ubiquitous in many real-world applications. Heterogeneous graph neural networks (HGNNs) as an efficient technique have shown superior capacity of dealing with heterogeneous graphs. Existing… read more here.
Keywords: neural network; heterogeneous graph; node representations; graph neural ... See more keywords
Domain Adaptive Graph Infomax via Conditional Adversarial Networks
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Network Science and Engineering"
DOI: 10.1109/tnse.2022.3201529
Abstract: The emerging graph neural networks (GNNs) have demonstrated impressive performance on the node classification problem in complex networks. However, existing GNNs are mainly devised to classify nodes in a (partially) labeled graph. To classify nodes… read more here.
Keywords: node representations; domain adaptive; adversarial networks; graph ... See more keywords