当前位置:
X-MOL 学术
›
arXiv.cs.DC
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Force2Vec: Parallel force-directed graph embedding
arXiv - CS - Distributed, Parallel, and Cluster Computing Pub Date : 2020-09-17 , DOI: arxiv-2009.10035 Md. Khaledur Rahman, Majedul Haque Sujon, Ariful Azad
arXiv - CS - Distributed, Parallel, and Cluster Computing Pub Date : 2020-09-17 , DOI: arxiv-2009.10035 Md. Khaledur Rahman, Majedul Haque Sujon, Ariful Azad
A graph embedding algorithm embeds a graph into a low-dimensional space such
that the embedding preserves the inherent properties of the graph. While graph
embedding is fundamentally related to graph visualization, prior work did not
exploit this connection explicitly. We develop Force2Vec that uses
force-directed graph layout models in a graph embedding setting with an aim to
excel in both machine learning (ML) and visualization tasks. We make Force2Vec
highly parallel by mapping its core computations to linear algebra and
utilizing multiple levels of parallelism available in modern processors. The
resultant algorithm is an order of magnitude faster than existing methods (43x
faster than DeepWalk, on average) and can generate embeddings from graphs with
billions of edges in a few hours. In comparison to existing methods, Force2Vec
is better in graph visualization and performs comparably or better in ML tasks
such as link prediction, node classification, and clustering. Source code is
available at https://github.com/HipGraph/Force2Vec.
中文翻译:
Force2Vec:平行力导向图嵌入
图嵌入算法将图嵌入到低维空间中,以便嵌入保留图的固有属性。虽然图嵌入从根本上与图可视化相关,但先前的工作并未明确利用这种联系。我们开发了 Force2Vec,它在图嵌入设置中使用力导向图布局模型,旨在在机器学习 (ML) 和可视化任务中表现出色。我们通过将其核心计算映射到线性代数并利用现代处理器中可用的多级并行性来使 Force2Vec 高度并行。由此产生的算法比现有方法快一个数量级(平均比 DeepWalk 快 43 倍),并且可以在几个小时内从具有数十亿条边的图中生成嵌入。与现有方法相比,Force2Vec 在图形可视化方面表现更好,在 ML 任务(例如链接预测、节点分类和聚类)中表现相当或更好。源代码可在 https://github.com/HipGraph/Force2Vec 获得。
更新日期:2020-09-22
中文翻译:
Force2Vec:平行力导向图嵌入
图嵌入算法将图嵌入到低维空间中,以便嵌入保留图的固有属性。虽然图嵌入从根本上与图可视化相关,但先前的工作并未明确利用这种联系。我们开发了 Force2Vec,它在图嵌入设置中使用力导向图布局模型,旨在在机器学习 (ML) 和可视化任务中表现出色。我们通过将其核心计算映射到线性代数并利用现代处理器中可用的多级并行性来使 Force2Vec 高度并行。由此产生的算法比现有方法快一个数量级(平均比 DeepWalk 快 43 倍),并且可以在几个小时内从具有数十亿条边的图中生成嵌入。与现有方法相比,Force2Vec 在图形可视化方面表现更好,在 ML 任务(例如链接预测、节点分类和聚类)中表现相当或更好。源代码可在 https://github.com/HipGraph/Force2Vec 获得。