arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.03434cs.LG
收藏

基于随机游走与一维卷积的单纯形数据学习

Learning From Simplicial Data Based on Random Walks and 1D Convolutions

RWTH Aachen University(亚琛工业大学)

Florian Frantzen, Michael T. Schaub

AI总结:

针对高阶拓扑计算模型计算成本高的问题,提出基于随机游走与一维卷积的单纯复形神经网络架构SCRaWl,可灵活控本且表达能力独特,实证性能优于同类模型。

摘要:

受基于图的深度学习方法在计算表达能力与模型灵活性方面存在局限的推动,近年来,针对超图、单纯复形等高阶拓扑域运行的计算模型研究热度激增。尽管这类模型提升后的表达能力确实能带来更优的分类性能,以及对底层系统更忠实的表征,但这类高阶模型的计算成本可能会急剧上升。为此,本文提出一种基于随机游走与快速一维卷积的单纯复形神经网络学习架构SCRaWl,该架构可在兼顾高阶关系的同时,通过调整所采用随机游走的长度与数量来控制计算成本的增幅。关键在于,由于采用基于随机游走的设计,该架构的表达能力经证明与现有消息传递式单纯形神经网络不可比拟。我们在真实世界数据集上对SCRaWl进行了实证评估,结果表明其性能优于其他单纯形神经网络。

英文摘要:

Triggered by limitations of graph-based deep learning methods in terms of computational expressivity and model flexibility, recent years have seen a surge of interest in computational models that operate on higher-order topological domains such as hypergraphs and simplicial complexes. While the increased expressivity of these models can indeed lead to a better classification performance and a more faithful representation of the underlying system, the computational cost of these higher-order models can increase dramatically. To this end, we here explore a simplicial complex neural network learning architecture based on random walks and fast 1D convolutions (SCRaWl), in which we can adjust the increase in computational cost by varying the length and number of random walks considered while accounting for higher-order relationships. Importantly, due to the random walk-based design, the expressivity of the proposed architecture is provably incomparable to that of existing message-passing simplicial neural networks. We empirically evaluate SCRaWl on real-world datasets and show that it outperforms other simplicial neural networks.

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。

↑