arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.04040cs.LGcs.DS
收藏

基于采样的图同态分类方法

Scaling up graph homomorphism for classification via sampling

LAMSADE, Université Paris-Dauphine, PSL(巴黎第九大学(多菲纳大学)LAMSADE实验室,PSL研究大学)

Paul Beaujean, Florian Sikora, Florian Yger

摘要:

特征生成是图机器学习研究的一个开放性课题。在本文中,我们研究使用图同态密度功能作为一个可扩展的替代同态数保留类似的理论性质和能力,考虑到归纳偏见。为此,我们提出了一个高性能的实现一个简单的采样算法,计算加法近似的同态密度。在图机器学习的背景下,我们在实验中证明,在样本同态密度上训练的简单线性模型可以在标准图分类数据集上实现与图神经网络相当的性能。最后,我们在合成数据的实验中表明,该算法的规模非常大的图时,实现布隆过滤器。

英文摘要:

Feature generation is an open topic of investigation in graph machine learning. In this paper, we study the use of graph homomorphism density features as a scalable alternative to homomorphism numbers which retain similar theoretical properties and ability to take into account inductive bias. For this, we propose a high-performance implementation of a simple sampling algorithm which computes additive approximations of homomorphism densities. In the context of graph machine learning, we demonstrate in experiments that simple linear models trained on sample homomorphism densities can achieve performance comparable to graph neural networks on standard graph classification datasets. Finally, we show in experiments on synthetic data that this algorithm scales to very large graphs when implemented with Bloom filters.

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。

↑