Dec 20, 2022 · As a mature technology to improve data quality in computer vision, data augmentation has also attracted increasing attention in graph domain. To advance research in …

Feb 1, 2023 · Graph data augmentation initiates data objects through structure modification or feature generation, a technique similar to data augmentation in CV and NLP. However, graphs …

Dec 9, 2024 · Data augmentation helps machine learning models perform better by making the most of existing data. It prevents overfitting, improves accuracy, and creates diversity in …

Sep 17, 2023 · In this paper, we propose ENGAGE (ExplaNation Guided data AuGmEntation), where explanation guides the contrastive augmentation process to preserve the key parts in …

Dec 8, 2022 · Graph neural networks, a powerful deep learning tool to model graph-structured data, have demonstrated remarkable performance on numerous graph learning tasks. To …

Our work studies graph data augmentation for graph neural networks (GNNs) in the context of improving semi-supervised node-classification. We discuss practical and theoretical …

Data augmentation for graph data involves creating modified versions of existing graphs to expand training datasets and improve machine learning model performance. Unlike tabular or …

We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations dur-ing training.

Feb 16, 2022 · Graph neural networks, a powerful deep learning tool to model graph-structured data, have demonstrated remarkable performance on numerous graph learning tasks. To …

Dec 20, 2022 · As a mature technology to improve data quality in computer vision, data augmentation has also attracted increasing attention in graph domain. To advance research in …