arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09676cs.LG
收藏

HyperMagNet:基于磁拉普拉斯算子的超图神经网络

HyperMagNet: A Magnetic Laplacian based Hypergraph Neural Network

University of Oregon(俄勒冈大学);Tufts University(塔夫茨大学);Pacific Northwest National Laboratory(西北太平洋国家实验室)

Tatyana Benko, Martin Buck, Ilya Amburg, Stephen J. Young, Sinan G. Aksoy

AI总结:

针对超图神经网络常简化超图为无向图导致信息丢失的问题,提出HyperMagNet,将超图表示为不可逆马尔可夫链并构建磁拉普拉斯算子,在节点分类任务中表现优于基于图简化的方法。

摘要:

在数据科学中,超图是对具有多路关系的数据的自然模型,而图仅能捕捉成对关系。尽管如此,许多已提出的超图神经网络通过对称矩阵表示将超图有效简化为无向图,可能丢失重要信息。我们提出一种超图神经网络的替代方法,将超图表示为不可逆马尔可夫链。我们利用该马尔可夫链构建复厄米拉普拉斯矩阵——磁拉普拉斯算子,作为所提超图神经网络的输入。我们针对节点分类任务研究HyperMagNet,并证明其相较于基于图简化的超图神经网络的有效性。

英文摘要:

In data science, hypergraphs are natural models for data exhibiting multi-way relations, whereas graphs only capture pairwise. Nonetheless, many proposed hypergraph neural networks effectively reduce hypergraphs to undirected graphs via symmetrized matrix representations, potentially losing important information. We propose an alternative approach to hypergraph neural networks in which the hypergraph is represented as a non-reversible Markov chain. We use this Markov chain to construct a complex Hermitian Laplacian matrix - the magnetic Laplacian - which serves as the input to our proposed hypergraph neural network. We study HyperMagNet for the task of node classification, and demonstrate its effectiveness over graph-reduction based hypergraph 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。

↑