.png){kind=icon}
返回
Mixup in Latent Geometry for Graph Classification
.png){kind=icon}
OA
AI
DOI：10.1109/TNSE.2024.3482188.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Mixup is a data augmentation method which can interpolate between existing data to create new samples. By enlarging the training distribution, it reduces the risk of over-fitting and improves generalization. Mixup is relatively straightforward to apply to image samples because pixels with equivalent coordinates in different images can be associated. However, alignment of distinct graphs with different sizes is non-trivial, thereby hindering the application of Mixup to graph data. Here we develop a novel algorithm to address this issue by exploiting the latent hyperbolic geometry which has been shown to underlie many real-world graphs. By considering global graph structure similarity and several fundamental structural features of graph models, we demonstrate that our mixup scheme leads to synthetic graphs whose structural features approximate the linear interpolation of parent graphs, a property important for avoiding the generation of mislabeled synthetic data. We apply the proposed algorithm to classify empirical graphs, and the results show that it improves classification performance on all six benchmark datasets and significantly enhances the generalization ability and robustness of graph neural networks.
Keyword:
Mixup
hyperbolic embedding
graph neural network
graph neural network
data augmentation
data augmentation
data augmentation
期刊
I
IF:
7.9
论文数:
2.6K
被引数:
10.0K
机构
引用论文
A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability基于混合的数据增强调查: 分类，方法，应用和可解释性
PREAI
分享收藏Altitudinal Gradients of Stable Isotopes in Lee-Slope Precipitation in the Canadian Rocky Mountains
OAAI
OAAI分享收藏Reduced -defensin expression is associated with inflammation and not NOD2 mutation status in ileal Crohn's disease.png)
GutOAAI
GutIF0
OAAI分享收藏分享收藏Spectral Entropies as Information-Theoretic Tools for Complex Network ComparisonPHYSICAL REVIEW XOAAI
PHYSICAL REVIEW XIF15.7
OAAI分享收藏
查看更多内容