arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.14264cs.LG
收藏

基于随机游动返回概率的持久图多尺度图签名

A Multi-scale Graph Signature for Persistence Diagrams based on Return Probabilities of Random Walks

Boston University(波士顿大学)

Chau Pham, Trung Dang, Peter Chin

摘要:

持久性图(PD)通常被表征为同源类的死亡和出生的集合,已经已知用于提供图结构的拓扑表示,这通常在机器学习任务中是有用的。先前的工作依赖于单个图签名来构造PD。在本文中,我们探讨了使用一个家庭的多尺度图签名,以提高拓扑特征的鲁棒性。我们提出了一个深度学习架构来处理这组输入。基准图分类数据集上的实验表明,我们提出的架构优于其他持久的同源性为基础的方法,并实现竞争力的性能相比,国家的最先进的方法,使用图神经网络。此外,我们的方法可以很容易地应用到大尺寸的输入图,因为它不会受到有限的可扩展性,这可能是一个问题的图核方法。

英文摘要:

Persistence diagrams (PDs), often characterized as sets of death and birth of homology class, have been known for providing a topological representation of a graph structure, which is often useful in machine learning tasks. Prior works rely on a single graph signature to construct PDs. In this paper, we explore the use of a family of multi-scale graph signatures to enhance the robustness of topological features. We propose a deep learning architecture to handle this set input. Experiments on benchmark graph classification datasets demonstrate that our proposed architecture outperforms other persistent homology-based methods and achieves competitive performance compared to state-of-the-art methods using graph neural networks. In addition, our approach can be easily applied to large size of input graphs as it does not suffer from limited scalability which can be an issue for graph kernel methods.

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。

↑