Mind the label shift of augmentation-based graph ood generalization
Abstract Out-of-distribution (OOD) generalization is an important issue for Graph Neural
Networks (GNNs). Recent works employ different graph editions to generate augmented …
Networks (GNNs). Recent works employ different graph editions to generate augmented …
Generative explanations for graph neural network: Methods and evaluations
Graph Neural Networks (GNNs) achieve state-of-the-art performance in various graph-
related tasks. However, the black-box nature often limits their interpretability and …
related tasks. However, the black-box nature often limits their interpretability and …
Mixupexplainer: Generalizing explanations for graph neural networks with data augmentation
Graph Neural Networks (GNNs) have received increasing attention due to their ability to
learn from graph-structured data. However, their predictions are often not interpretable. Post …
learn from graph-structured data. However, their predictions are often not interpretable. Post …
A survey on explainability of graph neural networks
Graph neural networks (GNNs) are powerful graph-based deep-learning models that have
gained significant attention and demonstrated remarkable performance in various domains …
gained significant attention and demonstrated remarkable performance in various domains …
Trustworthy graph learning: Reliability, explainability, and privacy protection
Deep graph learning (DGL) has achieved remarkable progress in both business and
scientific areas ranging from finance and e-commerce, to drug and advanced material …
scientific areas ranging from finance and e-commerce, to drug and advanced material …
Rumor detection with diverse counterfactual evidence
The growth in social media has exacerbated the threat of fake news to individuals and
communities. This draws increasing attention to developing efficient and timely rumor …
communities. This draws increasing attention to developing efficient and timely rumor …
Explainable Spatio-Temporal Graph Neural Networks
Spatio-temporal graph neural networks (STGNNs) have gained popularity as a powerful tool
for effectively modeling spatio-temporal dependencies in diverse real-world urban …
for effectively modeling spatio-temporal dependencies in diverse real-world urban …
Optimizing ood detection in molecular graphs: A novel approach with diffusion models
Despite the recent progress of molecular representation learning, its effectiveness is
assumed on the close-world assumptions that training and testing graphs are from identical …
assumed on the close-world assumptions that training and testing graphs are from identical …
Topoimb: Toward topology-level imbalance in learning from graphs
Graph serves as a powerful tool for modeling data that has an underlying structure in non-
Euclidean space, by encoding relations as edges and entities as nodes. Despite …
Euclidean space, by encoding relations as edges and entities as nodes. Despite …
A survey on privacy in graph neural networks: Attacks, preservation, and applications
Graph Neural Networks (GNNs) have gained significant attention owing to their ability to
handle graph-structured data and the improvement in practical applications. However, many …
handle graph-structured data and the improvement in practical applications. However, many …