谱网络嵌入:一种基于稀疏性的快速可扩展方法
Spectral Network Embedding: A Fast and Scalable Method via Sparsity
摘要:
网络嵌入旨在学习网络中节点的低维表示,同时保留网络结构和固有属性。最近,由于下游网络学习任务(如节点分类、链接预测和可视化)的重大进展,它引起了极大的关注。然而,大多数现有的网络嵌入方法遭受昂贵的计算,由于大量的网络。在本文中,我们提出了一个$10\times \sim 100\times$更快的网络嵌入方法,称为Progle,通过优雅地利用在线网络的稀疏性和频谱分析。在Progle中,我们首先构造\textit{sparse}邻近矩阵,并通过稀疏矩阵分解有效地训练网络嵌入。然后,我们通过频谱分析引入网络传播模式,将局部和全局结构信息嵌入。此外,该模型可以推广到集成网络信息到其他未经充分训练的嵌入速度。受益于稀疏谱网络嵌入,我们在四个不同数据集上的实验表明,Progle在准确性方面优于或相当于最先进的无监督比较方法--DeepWalk,LINE,node 2 vec,GraRep和HOPE,而$10\times$比最快的基于word 2 vec的方法更快。最后,我们验证了Progle在实际大规模网络和多尺度合成网络中的可扩展性。
英文摘要:
Network embedding aims to learn low-dimensional representations of nodes in a network, while the network structure and inherent properties are preserved. It has attracted tremendous attention recently due to significant progress in downstream network learning tasks, such as node classification, link prediction, and visualization. However, most existing network embedding methods suffer from the expensive computations due to the large volume of networks. In this paper, we propose a $10\times \sim 100\times$ faster network embedding method, called Progle, by elegantly utilizing the sparsity property of online networks and spectral analysis. In Progle, we first construct a \textit{sparse} proximity matrix and train the network embedding efficiently via sparse matrix decomposition. Then we introduce a network propagation pattern via spectral analysis to incorporate local and global structure information into the embedding. Besides, this model can be generalized to integrate network information into other insufficiently trained embeddings at speed. Benefiting from sparse spectral network embedding, our experiment on four different datasets shows that Progle outperforms or is comparable to state-of-the-art unsupervised comparison approaches---DeepWalk, LINE, node2vec, GraRep, and HOPE, regarding accuracy, while is $10\times$ faster than the fastest word2vec-based method. Finally, we validate the scalability of Progle both in real large-scale networks and multiple scales of synthetic 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。