arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.04314cs.LGcs.AIstat.ML
收藏

图神经网络随机数据扩充的系统方法

A systematic approach to random data augmentation on graph neural networks

Technische Universität Kaiserslautern(凯泽斯劳滕工业大学);Technische Universität Darmstadt(达姆施塔特工业大学)

Billy Joe Franks, Markus Anders, Marius Kloft, Pascal Schweitzer

摘要:

随机数据扩充(RDAs)是关于可证明通用的实用图神经网络的最新技术。现有的RDA在术语、方法、基准和评价指标方面存在很大差异。这不仅使从业者越来越难以决定将哪种技术应用于给定的问题,而且还阻碍了系统的改进。我们提出了一个新的综合框架,捕捉所有以前的RDA技术。在理论方面,除其他结果外,我们正式证明,在自然条件下,我们的框架的所有实例是普遍的。在实践方面,我们开发了一种方法来系统和自动训练RDA。这反过来又使我们能够公正和客观地比较所有现有的RDA。新的RDA自然会从我们的方法中产生,我们的实验表明它们改进了最先进的技术。

英文摘要:

Random data augmentations (RDAs) are state of the art regarding practical graph neural networks that are provably universal. There is great diversity regarding terminology, methodology, benchmarks, and evaluation metrics used among existing RDAs. Not only does this make it increasingly difficult for practitioners to decide which technique to apply to a given problem, but it also stands in the way of systematic improvements. We propose a new comprehensive framework that captures all previous RDA techniques. On the theoretical side, among other results, we formally prove that under natural conditions all instantiations of our framework are universal. On the practical side, we develop a method to systematically and automatically train RDAs. This in turn enables us to impartially and objectively compare all existing RDAs. New RDAs naturally emerge from our approach, and our experiments demonstrate that they improve the state of the art.

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。

↑