DGSLN: differentiable graph structure learning neural network for robust graph representations
Recently, graph neural networks (GNNs) have been widely used for graph representation
learning, where the central idea is to recursively aggregate neighborhood information to …
learning, where the central idea is to recursively aggregate neighborhood information to …
[PDF][PDF] Deep graph structure learning for robust representations: A survey
Abstract Graph Neural Networks (GNNs) are widely used for analyzing graph-structured
data. Most GNN methods are highly sensitive to the quality of graph structures and usually …
data. Most GNN methods are highly sensitive to the quality of graph structures and usually …
Eigen-GNN: A graph structure preserving plug-in for GNNs
Graph Neural Networks (GNNs) are emerging machine learning models on graphs.
Although sufficiently deep GNNs are shown theoretically capable of fully preserving graph …
Although sufficiently deep GNNs are shown theoretically capable of fully preserving graph …
Learning graph normalization for graph neural networks
Abstract Graph Neural Networks (GNNs) have emerged as a useful paradigm to process
graph-structured data. Usually, GNNs are stacked to multiple layers and node …
graph-structured data. Usually, GNNs are stacked to multiple layers and node …
GraphSAGE++: Weighted Multi-scale GNN for Graph Representation Learning
E Jiawei, Y Zhang, S Yang, H Wang, X Xia… - Neural Processing …, 2024 - Springer
Graph neural networks (GNNs) have emerged as a powerful tool in graph representation
learning. However, they are increasingly challenged by over-smoothing as network depth …
learning. However, they are increasingly challenged by over-smoothing as network depth …
Learning invariant representations of graph neural networks via cluster generalization
Graph neural networks (GNNs) have become increasingly popular in modeling graph-
structured data due to their ability to learn node representations by aggregating local …
structured data due to their ability to learn node representations by aggregating local …
GSLB: the graph structure learning benchmark
Abstract Graph Structure Learning (GSL) has recently garnered considerable attention due
to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the …
to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the …
Propagation enhanced neural message passing for graph representation learning
Graph Neural Network (GNN) is capable of applying deep neural networks to graph
domains. Recently, Message Passing Neural Networks (MPNNs) have been proposed to …
domains. Recently, Message Passing Neural Networks (MPNNs) have been proposed to …
Towards unsupervised deep graph structure learning
In recent years, graph neural networks (GNNs) have emerged as a successful tool in a
variety of graph-related applications. However, the performance of GNNs can be …
variety of graph-related applications. However, the performance of GNNs can be …
Taxonomy of benchmarks in graph representation learning
Abstract Graph Neural Networks (GNNs) extend the success of neural networks to graph-
structured data by accounting for their intrinsic geometry. While extensive research has been …
structured data by accounting for their intrinsic geometry. While extensive research has been …