arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.12056cs.SIcs.LG
收藏

DSSLP:一种分布式半监督链接预测框架

DSSLP: A Distributed Framework for Semi-supervised Link Prediction

Ant Financial Services Group(蚂蚁金融服务集团)

Dalong Zhang, Xianzheng Song, Ziqi Liu, Zhiqiang Zhang, Xin Huang, Lin Wang, Jun Zhou

摘要:

链接预测广泛应用于商家推荐、欺诈交易检测等工业应用中,然而在具有数十亿节点和边的工业规模图上训练和部署链接预测模型是一个巨大的挑战。在这项工作中,我们提出了一个用于半监督链接预测问题的可扩展和分布式框架(名为DSSLP),该框架能够处理工业规模的图。DSSLP不是在整个图上训练模型,而是在小批量环境下对节点的\emph{$k$-hops neighborhood}进行训练,这有助于减少输入图的规模并分布训练过程。为了有效地生成反例,DSSLP包含分布式批处理运行时采样模块。它实现了统一和动态的采样方法,并能够自适应地构建正面和负面的例子来指导训练过程。此外,DSSLP提出了一种模型分裂策略,以加快链接预测任务的推理过程的速度。实验结果表明,DSSLP的有效性和效率在几个公共数据集以及真实世界的数据集的工业规模的图。

英文摘要:

Link prediction is widely used in a variety of industrial applications, such as merchant recommendation, fraudulent transaction detection, and so on. However, it's a great challenge to train and deploy a link prediction model on industrial-scale graphs with billions of nodes and edges. In this work, we present a scalable and distributed framework for semi-supervised link prediction problem (named DSSLP), which is able to handle industrial-scale graphs. Instead of training model on the whole graph, DSSLP is proposed to train on the \emph{$k$-hops neighborhood} of nodes in a mini-batch setting, which helps reduce the scale of the input graph and distribute the training procedure. In order to generate negative examples effectively, DSSLP contains a distributed batched runtime sampling module. It implements uniform and dynamic sampling approaches, and is able to adaptively construct positive and negative examples to guide the training process. Moreover, DSSLP proposes a model-split strategy to accelerate the speed of inference process of the link prediction task. Experimental results demonstrate that the effectiveness and efficiency of DSSLP in serval public datasets as well as real-world datasets of industrial-scale graphs.

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。

↑