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 1802.04948cs.LG
收藏

Graph2Seq:可扩展的图学习动态

Graph2Seq: Scalable Learning Dynamics for Graphs

Massachusetts Institute of Technology(麻省理工学院);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Shaileshh Bojja Venkatakrishnan, Mohammad Alizadeh, Pramod Viswanath

摘要:

神经网络已被证明是一个有效的工具,学习算法的图形结构的数据。然而,图表示技术--将图转换为实值向量以用于神经网络--仍处于起步阶段。最近的工作已经提出了几种方法(例如,图卷积网络),但是这些方法难以缩放和推广到具有不同大小和形状的图。我们提出了Graph 2Seq,一种将图的顶点表示为无限时间序列的新技术。通过不将表示限制在固定的维度,Graph 2Seq可以自然地扩展到任意大小和形状的图形。Graph 2Seq也是可逆的,允许从序列中完全恢复图结构。通过分析一个正式的图表示计算模型,我们表明,一个无界序列是必要的可扩展性。我们使用Graph 2Seq的实验结果显示了强大的泛化能力和对各种图组合优化问题的最新性能。

英文摘要:

Neural networks have been shown to be an effective tool for learning algorithms over graph-structured data. However, graph representation techniques---that convert graphs to real-valued vectors for use with neural networks---are still in their infancy. Recent works have proposed several approaches (e.g., graph convolutional networks), but these methods have difficulty scaling and generalizing to graphs with different sizes and shapes. We present Graph2Seq, a new technique that represents vertices of graphs as infinite time-series. By not limiting the representation to a fixed dimension, Graph2Seq scales naturally to graphs of arbitrary sizes and shapes. Graph2Seq is also reversible, allowing full recovery of the graph structure from the sequences. By analyzing a formal computational model for graph representation, we show that an unbounded sequence is necessary for scalability. Our experimental results with Graph2Seq show strong generalization and new state-of-the-art performance on a variety of graph combinatorial optimization problems.

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。

↑