arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1710.03059cs.LG
收藏

利用嵌入传播学习图表示

Learning Graph Representations with Embedding Propagation

NEC Labs Europe(NEC欧洲实验室)

Alberto Garcia-Duran, Mathias Niepert

摘要:

我们提出了嵌入传播(EP),一个无监督学习框架的图结构数据。EP通过在相邻节点之间传递两种类型的消息来学习图的矢量表示。转发消息由标签表示组成,例如与节点相关联的单词和其他属性的表示。反向消息由聚合标签表示和应用重建损失产生的梯度组成。节点表示最终从其标签的表示中计算出来。由于参数和超参数显著减少,EP的实例在一系列基准数据集上与最先进的无监督和半监督学习方法竞争并且通常优于它们。

英文摘要:

We propose Embedding Propagation (EP), an unsupervised learning framework for graph-structured data. EP learns vector representations of graphs by passing two types of messages between neighboring nodes. Forward messages consist of label representations such as representations of words and other attributes associated with the nodes. Backward messages consist of gradients that result from aggregating the label representations and applying a reconstruction loss. Node representations are finally computed from the representation of their labels. With significantly fewer parameters and hyperparameters an instance of EP is competitive with and often outperforms state of the art unsupervised and semi-supervised learning methods on a range of benchmark data sets.

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。

↑