arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1605.02115cs.SIphysics.soc-ph
收藏

不要走路,斯基普!多尺度网络嵌入的在线学习

Don't Walk, Skip! Online Learning of Multi-scale Network Embeddings

Bryan Perozzi, Vivek Kulkarni, Haochen Chen, Steven Skiena

摘要:

我们提出了Walklets,一种新的方法,用于学习网络中顶点的多尺度表示。与以前的作品相比,这些表示明确编码多尺度顶点关系的方式是解析推导。Walklet通过对图的顶点上的短随机游走进行子采样来生成这些多尺度关系。通过“跳过”每个随机游走中的步骤,我们的方法生成了一个顶点对的语料库,这些顶点对可以通过固定长度的路径到达。然后,该语料库可以用于学习一系列潜在表示,每个潜在表示从邻接矩阵中连续捕获更高阶的关系。我们证明了Walklets的潜在表示在多个多标签网络分类任务的社交网络,如BlogCatalog,DBLP,Flickr和YouTube的功效。我们的研究结果表明,Walklets优于基于神经矩阵分解的新方法。具体来说,在具有挑战性的多标签分类任务上,我们的表现比DeepWalk高出10%,比LINE高出58%。最后,Walklets是一种在线算法,可以轻松扩展到具有数百万个顶点和边的图形。

英文摘要:

We present Walklets, a novel approach for learning multiscale representations of vertices in a network. In contrast to previous works, these representations explicitly encode multiscale vertex relationships in a way that is analytically derivable. Walklets generates these multiscale relationships by subsampling short random walks on the vertices of a graph. By `skipping' over steps in each random walk, our method generates a corpus of vertex pairs which are reachable via paths of a fixed length. This corpus can then be used to learn a series of latent representations, each of which captures successively higher order relationships from the adjacency matrix. We demonstrate the efficacy of Walklets's latent representations on several multi-label network classification tasks for social networks such as BlogCatalog, DBLP, Flickr, and YouTube. Our results show that Walklets outperforms new methods based on neural matrix factorization. Specifically, we outperform DeepWalk by up to 10% and LINE by 58% Micro-F1 on challenging multi-label classification tasks. Finally, Walklets is an online algorithm, and can easily scale to graphs with millions of vertices and edges.

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。

↑