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 1907.01705cs.LGstat.ML
收藏

大规模图嵌入

Graph Embeddings at Scale

Capital One(第一资本)

C. Bayan Bruss, Anish Khazane, Jonathan Rider, Richard Serpe, Saurabh Nagrecha, Keegan E. Hines

摘要:

图嵌入是一种流行的算法方法,用于为网络中的各个顶点创建矢量表示。大规模训练这些算法对于创建可用于分类、排名、推荐和其他行业常见应用的嵌入非常重要。虽然存在用于在大型数据集上训练图嵌入的工业系统,但这些分布式架构中的许多都被迫在许多工作节点上划分大量数据和模型逻辑。在本文中,我们提出了一个分布式的基础设施,完全避免图分区,动态创建大小受限的计算图的工人节点,并使用高效的索引操作更新嵌入,使系统的规模运作。我们表明,我们的系统可以扩展现有的嵌入算法- skip-gram -训练上的开放源代码的网络(68万个顶点)和内部异构图(50万个顶点)。我们衡量我们的系统性能的两个关键的定量指标:链接预测精度和收敛速度。我们通过分析更多数量的工作节点如何实际提高系统在上述指标上的性能来结束这项工作,并讨论我们严格评估系统产生的嵌入向量的下一步措施。

英文摘要:

Graph embedding is a popular algorithmic approach for creating vector representations for individual vertices in networks. Training these algorithms at scale is important for creating embeddings that can be used for classification, ranking, recommendation and other common applications in industry. While industrial systems exist for training graph embeddings on large datasets, many of these distributed architectures are forced to partition copious amounts of data and model logic across many worker nodes. In this paper, we propose a distributed infrastructure that completely avoids graph partitioning, dynamically creates size constrained computational graphs across worker nodes, and uses highly efficient indexing operations for updating embeddings that allow the system to function at scale. We show that our system can scale an existing embeddings algorithm - skip-gram - to train on the open-source Friendster network (68 million vertices) and on an internal heterogeneous graph (50 million vertices). We measure the performance of our system on two key quantitative metrics: link-prediction accuracy and rate of convergence. We conclude this work by analyzing how a greater number of worker nodes actually improves our system's performance on the aforementioned metrics and discuss our next steps for rigorously evaluating the embedding vectors produced by our system.

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。

↑