arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00722cs.LGcs.AI
收藏

GABO:基于双层优化的图扩充算法

GABO: Graph Augmentations with Bi-level Optimization

Stanford University(斯坦福大学)

Heejung W. Chung, Avoy Datta, Chris Waites

摘要:

数据增强是指通过增强训练样本来改进模型泛化的广泛技术。通常,这样的方法需要关于手头数据集的领域知识,产生了大量的最近的文献,围绕自动化技术的数据增强。在这项工作中,我们采用这样的方法,双层优化,以解决ogbg-molhiv数据集上的图分类问题。我们的最佳性能增强使用GIN+虚拟分类器实现了77.77%的测试ROCAUC分数,这使其成为排行榜上该分类器最有效的增强器。该框架将GIN层增强生成器与偏置变换相结合,并优于使用最先进的FLAG增强的相同分类器。

英文摘要:

Data augmentation refers to a wide range of techniques for improving model generalization by augmenting training examples. Oftentimes such methods require domain knowledge about the dataset at hand, spawning a plethora of recent literature surrounding automated techniques for data augmentation. In this work we apply one such method, bilevel optimization, to tackle the problem of graph classification on the ogbg-molhiv dataset. Our best performing augmentation achieved a test ROCAUC score of 77.77 % with a GIN+virtual classifier, which makes it the most effective augmenter for this classifier on the leaderboard. This framework combines a GIN layer augmentation generator with a bias transformation and outperforms the same classifier augmented using the state-of-the-art FLAG augmentation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑