Representation learning for dynamic graphs: A survey
Graphs arise naturally in many real-world applications including social networks,
recommender systems, ontologies, biology, and computational finance. Traditionally …
recommender systems, ontologies, biology, and computational finance. Traditionally …
Anomaly detection with convolutional graph neural networks
O Atkinson, A Bhardwaj, C Englert… - Journal of High Energy …, 2021 - Springer
A bstract We devise an autoencoder based strategy to facilitate anomaly detection for
boosted jets, employing Graph Neural Networks (GNNs) to do so. To overcome known …
boosted jets, employing Graph Neural Networks (GNNs) to do so. To overcome known …
Federated multidomain learning with graph ensemble autoencoder GMM for emotion recognition
Facial expression cognition technology continues to face challenges from certain
perspectives despite the fact that there have been significant recent learning advances in …
perspectives despite the fact that there have been significant recent learning advances in …
Gravity-inspired graph autoencoders for directed link prediction
Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful
node embedding methods. In particular, graph AE and VAE were successfully leveraged to …
node embedding methods. In particular, graph AE and VAE were successfully leveraged to …
Latent representation learning in biology and translational medicine
A Kopf, M Claassen - Patterns, 2021 - cell.com
Current data generation capabilities in the life sciences render scientists in an apparently
contradicting situation. While it is possible to simultaneously measure an ever-increasing …
contradicting situation. While it is possible to simultaneously measure an ever-increasing …
Graph interpretation, summarization and visualization techniques: a review and open research issues
Graphs has been a ubiquitous way of representing heterogeneous data. There are many
studies focused on graph learning highlighting the approaches for graph data extraction …
studies focused on graph learning highlighting the approaches for graph data extraction …
Point2skeleton: Learning skeletal representations from point clouds
Abstract We introduce Point2Skeleton, an unsupervised method to learn skeletal
representations from point clouds. Existing skeletonization methods are limited to tubular …
representations from point clouds. Existing skeletonization methods are limited to tubular …
Dual feature interaction-based graph convolutional network
Graphs are widely used to model various practical applications. In recent years, graph
convolution networks (GCNs) have attracted increasing attention due to the extension of …
convolution networks (GCNs) have attracted increasing attention due to the extension of …
Variational inference for training graph neural networks in low-data regime through joint structure-label estimation
Graph Neural Networks (GNNs) are one of the prominent methods to solve semi-supervised
learning on graphs. However, most of the existing GNN models often need sufficient …
learning on graphs. However, most of the existing GNN models often need sufficient …
Exploring structure-adaptive graph learning for robust semi-supervised classification
X Gao, W Hu, Z Guo - 2020 ieee international conference on …, 2020 - ieeexplore.ieee.org
Graph Convolutional Neural Networks (GCNNs) are generalizations of CNNs to graph-
structured data, in which convolution is guided by the graph topology. In many cases where …
structured data, in which convolution is guided by the graph topology. In many cases where …