Self-supervised learning of graph neural networks: A unified review
Deep models trained in supervised mode have achieved remarkable success on a variety of
tasks. When labeled samples are limited, self-supervised learning (SSL) is emerging as a …
tasks. When labeled samples are limited, self-supervised learning (SSL) is emerging as a …
A comprehensive survey on graph neural networks
Deep learning has revolutionized many machine learning tasks in recent years, ranging
from image classification and video processing to speech recognition and natural language …
from image classification and video processing to speech recognition and natural language …
Vision gnn: An image is worth graph of nodes
Network architecture plays a key role in the deep learning-based computer vision system.
The widely-used convolutional neural network and transformer treat the image as a grid or …
The widely-used convolutional neural network and transformer treat the image as a grid or …
Representing long-range context for graph neural networks with global attention
Graph neural networks are powerful architectures for structured datasets. However, current
methods struggle to represent long-range dependencies. Scaling the depth or width of …
methods struggle to represent long-range dependencies. Scaling the depth or width of …
Graph self-supervised learning: A survey
Deep learning on graphs has attracted significant interests recently. However, most of the
works have focused on (semi-) supervised learning, resulting in shortcomings including …
works have focused on (semi-) supervised learning, resulting in shortcomings including …
Weisfeiler and lehman go cellular: Cw networks
Abstract Graph Neural Networks (GNNs) are limited in their expressive power, struggle with
long-range interactions and lack a principled way to model higher-order structures. These …
long-range interactions and lack a principled way to model higher-order structures. These …
Tudataset: A collection of benchmark datasets for learning with graphs
Recently, there has been an increasing interest in (supervised) learning with graph data,
especially using graph neural networks. However, the development of meaningful …
especially using graph neural networks. However, the development of meaningful …
Infogcl: Information-aware graph contrastive learning
Various graph contrastive learning models have been proposed to improve the performance
of tasks on graph datasets in recent years. While effective and prevalent, these models are …
of tasks on graph datasets in recent years. While effective and prevalent, these models are …
Self-supervised learning on graphs: Contrastive, generative, or predictive
Deep learning on graphs has recently achieved remarkable success on a variety of tasks,
while such success relies heavily on the massive and carefully labeled data. However …
while such success relies heavily on the massive and carefully labeled data. However …
On the bottleneck of graph neural networks and its practical implications
Since the proposal of the graph neural network (GNN) by Gori et al.(2005) and Scarselli et
al.(2008), one of the major problems in training GNNs was their struggle to propagate …
al.(2008), one of the major problems in training GNNs was their struggle to propagate …