Learning invariant graph representations for out-of-distribution generalization
Graph representation learning has shown effectiveness when testing and training graph
data come from the same distribution, but most existing approaches fail to generalize under …
data come from the same distribution, but most existing approaches fail to generalize under …
Learning substructure invariance for out-of-distribution molecular representations
Molecule representation learning (MRL) has been extensively studied and current methods
have shown promising power for various tasks, eg, molecular property prediction and target …
have shown promising power for various tasks, eg, molecular property prediction and target …
Unleashing the power of graph data augmentation on covariate distribution shift
The issue of distribution shifts is emerging as a critical concern in graph representation
learning. From the perspective of invariant learning and stable learning, a recently well …
learning. From the perspective of invariant learning and stable learning, a recently well …
Learning causally invariant representations for out-of-distribution generalization on graphs
Despite recent success in using the invariance principle for out-of-distribution (OOD)
generalization on Euclidean data (eg, images), studies on graph data are still limited …
generalization on Euclidean data (eg, images), studies on graph data are still limited …
Good: A graph out-of-distribution benchmark
Abstract Out-of-distribution (OOD) learning deals with scenarios in which training and test
data follow different distributions. Although general OOD problems have been intensively …
data follow different distributions. Although general OOD problems have been intensively …
A comprehensive survey on graph reduction: Sparsification, coarsening, and condensation
Many real-world datasets can be naturally represented as graphs, spanning a wide range of
domains. However, the increasing complexity and size of graph datasets present significant …
domains. However, the increasing complexity and size of graph datasets present significant …
Debiasing graph neural networks via learning disentangled causal substructure
Abstract Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by
learning the correlation between the input graphs and labels. However, by presenting a …
learning the correlation between the input graphs and labels. However, by presenting a …
Demystifying structural disparity in graph neural networks: Can one size fit all?
Abstract Recent studies on Graph Neural Networks (GNNs) provide both empirical and
theoretical evidence supporting their effectiveness in capturing structural patterns on both …
theoretical evidence supporting their effectiveness in capturing structural patterns on both …
Dynamic graph neural networks under spatio-temporal distribution shift
Dynamic graph neural networks (DyGNNs) have demonstrated powerful predictive abilities
by exploiting graph structural and temporal dynamics. However, the existing DyGNNs fail to …
by exploiting graph structural and temporal dynamics. However, the existing DyGNNs fail to …
Simplifying and empowering transformers for large-graph representations
Learning representations on large-sized graphs is a long-standing challenge due to the inter-
dependence nature involved in massive data points. Transformers, as an emerging class of …
dependence nature involved in massive data points. Transformers, as an emerging class of …