Towards understanding generalization of graph neural networks
H Tang, Y Liu - International Conference on Machine …, 2023 - proceedings.mlr.press
Graph neural networks (GNNs) are widely used in machine learning for graph-structured
data. Even though GNNs have achieved remarkable success in real-world applications …
data. Even though GNNs have achieved remarkable success in real-world applications …
Approximately equivariant graph networks
Graph neural networks (GNNs) are commonly described as being permutation equivariant
with respect to node relabeling in the graph. This symmetry of GNNs is often compared to …
with respect to node relabeling in the graph. This symmetry of GNNs is often compared to …
Wl meet vc
Recently, many works studied the expressive power of graph neural networks (GNNs) by
linking it to the $1 $-dimensional Weisfeiler-Leman algorithm ($1\text {-}\mathsf {WL} $) …
linking it to the $1 $-dimensional Weisfeiler-Leman algorithm ($1\text {-}\mathsf {WL} $) …
Generalization in graph neural networks: Improved pac-bayesian bounds on graph diffusion
Graph neural networks are widely used tools for graph prediction tasks. Motivated by their
empirical performance, prior works have developed generalization bounds for graph neural …
empirical performance, prior works have developed generalization bounds for graph neural …
Graph convolution network based recommender systems: Learning guarantee and item mixture powered strategy
Inspired by their powerful representation ability on graph-structured data, Graph Convolution
Networks (GCNs) have been widely applied to recommender systems, and have shown …
Networks (GCNs) have been widely applied to recommender systems, and have shown …
What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
Graph Transformers, which incorporate self-attention and positional encoding, have recently
emerged as a powerful architecture for various graph learning tasks. Despite their …
emerged as a powerful architecture for various graph learning tasks. Despite their …
Empowering simple graph convolutional networks
Many neural networks for graphs are based on the graph convolution (GC) operator,
proposed more than a decade ago. Since then, many alternative definitions have been …
proposed more than a decade ago. Since then, many alternative definitions have been …
Weisfeiler-Leman at the margin: When more expressivity matters
The Weisfeiler-Leman algorithm ($1 $-WL) is a well-studied heuristic for the graph
isomorphism problem. Recently, the algorithm has played a prominent role in understanding …
isomorphism problem. Recently, the algorithm has played a prominent role in understanding …
Information-Theoretic Generalization Bounds for Transductive Learning and its Applications
H Tang, Y Liu - arXiv preprint arXiv:2311.04561, 2023 - arxiv.org
In this paper, we develop data-dependent and algorithm-dependent generalization bounds
for transductive learning algorithms in the context of information theory for the first time. We …
for transductive learning algorithms in the context of information theory for the first time. We …
Representation power of graph convolutions: Neural tangent kernel analysis
The fundamental principle of Graph Neural Networks (GNNs) is to exploit the structural
information of the data by aggregating the neighboring nodes using agraph convolution' …
information of the data by aggregating the neighboring nodes using agraph convolution' …