当前位置: X-MOL 学术arXiv.cs.SI › 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.)
MultiWalk: A Framework to Generate Node Embeddings Based on an Ensemble of Walk Methods
arXiv - CS - Social and Information Networks Pub Date : 2021-02-23 , DOI: arxiv-2102.11691
Kaléu Delphino

Graph embeddings are low dimensional representations of nodes, edges or whole graphs. Such representations allow for data in a network format to be used along with machine learning models for a variety of tasks (e.g., node classification), where using a similarity matrix would be impractical. In recent years, many methods for graph embedding generation have been created based on the idea of random walks. We propose MultiWalk, a framework that uses an ensemble of these methods to generate the embeddings. Our experiments show that the proposed framework, using an ensemble composed of two state-of-the-art methods, can generate embeddings that perform better in classification tasks than each method in isolation.

中文翻译:

MultiWalk:一种基于行走方法的集合生成节点嵌入的框架

图嵌入是节点,边或整个图的低维表示。这样的表示允许将网络格式的数据与机器学习模型一起用于各种任务(例如,节点分类),其中使用相似性矩阵是不切实际的。近年来,基于随机游走的想法已经创建了许多用于图形嵌入生成的方法。我们提出了MultiWalk,一个使用这些方法的整体来生成嵌入的框架。我们的实验表明,所提出的框架使用由两种最先进的方法组成的集合,可以生成在分类任务中比单独使用每种方法更好的嵌入。
更新日期:2021-02-24
down
wechat
bug