Automated Data Augmentations for Graph Classification
Data augmentations are effective in improving the invariance of learning machines. We argue that the core challenge of data augmentations lies in designing data transformations that preserve labels. This is relatively straightforward for images, but much more challenging for graphs. In this work, we propose GraphAug, a novel automated data augmentation method aiming at computing label-invariant augmentations for graph classification. Instead of using uniform transformations as in existing studies, GraphAug uses an automated augmentation model to avoid compromising critical label-related information of the graph, thereby producing label-invariant augmentations at most times. To ensure label-invariance, we develop a training method based on reinforcement learning to maximize an estimated label-invariance probability. Experiments show that GraphAug outperforms previous graph augmentation methods on various graph classification tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationData AugmentationGraph ClassificationSimilar Papers 제목 키워드 기반
Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations
In this study, we undertake a reproducibility analysis of 'Learning Fair Graph Representations Via Automated Data Augmentations' by Ling et al. (2022). We assess the validity of the original claims focused on node classi…
FairnessLink PredictionNode ClassificationGraph Contrastive Learning Automated
Self-supervised learning on graph-structured data has drawn recent interest for learning generalizable, transferable and robust representations from unlabeled graphs. Among many, graph contrastive learning (GraphCL) has …
Contrastive LearningRepresentation LearningSelf-Supervised LearningBeyond Cropping and Rotation: Automated Evolution of Powerful Task-Specific Augmentations with Generative Models
Data augmentation has long been a cornerstone for reducing overfitting in vision models, with methods like AutoAugment automating the design of task-specific augmentations. Recent advances in generative models, such as c…
Image AugmentationFew-Shot LearningData AugmentationHybrid Augmented Automated Graph Contrastive Learning
Graph augmentations are essential for graph contrastive learning. Most existing works use pre-defined random augmentations, which are usually unable to adapt to different input graphs and fail to consider the impact of d…
Contrastive LearningExplanation-Preserving Augmentation for Semi-Supervised Graph Representation Learning
Graph representation learning (GRL), enhanced by graph augmentation methods, has emerged as an effective technique achieving performance improvements in wide tasks such as node classification and graph classification. In…
Graph ClassificationGraph Representation LearningNode ClassificationRepresentation Learning