开发用于训练图形的可扩展解决方案,用于链路预测任务的Neural网络(GNNS)由于具有高计算成本和巨大内存占用的高数据依赖性,因此由于高数据依赖性而具有挑战性。我们提出了一种新的方法,用于缩放知识图形嵌入模型的培训,以满足这些挑战。为此,我们提出了以下算法策略:自给自足的分区,基于约束的负采样和边缘迷你批量培训。两者都是分区策略和基于约束的负面采样,避免在训练期间交叉分区数据传输。在我们的实验评估中,我们表明,我们基于GNN的知识图形嵌入模型的缩放解决方案在基准数据集中实现了16倍的加速,同时将可比的模型性能作为标准度量的非分布式方法。
translated by 谷歌翻译
Cutting planes are a crucial component of state-of-the-art mixed-integer programming solvers, with the choice of which subset of cuts to add being vital for solver performance. We propose new distance-based measures to qualify the value of a cut by quantifying the extent to which it separates relevant parts of the relaxed feasible set. For this purpose, we use the analytic centers of the relaxation polytope or of its optimal face, as well as alternative optimal solutions of the linear programming relaxation. We assess the impact of the choice of distance measure on root node performance and throughout the whole branch-and-bound tree, comparing our measures against those prevalent in the literature. Finally, by a multi-output regression, we predict the relative performance of each measure, using static features readily available before the separation process. Our results indicate that analytic center-based methods help to significantly reduce the number of branch-and-bound nodes needed to explore the search space and that our multiregression approach can further improve on any individual method.
translated by 谷歌翻译
在实际应用桥梁称重(BWIM)方法中,车辆通过期间车轮或车轴的位置在大多数情况下是先决条件。为了避免使用常规轴检测器和桥梁类型特定的方法,我们提出了一种新的方法来通过在桥梁的任何点上放置加速度计来检测轴检测。为了开发尽可能简单且可理解的模型,将轴检测任务实现为二进制分类问题,而不是回归问题。该模型被用作完全卷积网络,以连续小波变换的形式处理信号。这允许在单个步骤中以最大效率处理任何长度的段落,同时在单个评估中使用多个量表。这使我们的方法能够在桥结构的任何位置使用加速信号,该位置用作虚拟轴检测器(VADS),而无需仅限于特定的结构类型的桥梁。为了测试提出的方法,我们分析了在长途交通线的钢槽铁路桥上记录的3787列火车通道。我们在测量数据上的结果表明,我们的模型检测到轴的95%,因此,正确检测到了134,800个以前看不见的轴的128,599。总共可以以20厘米的最大空间误差检测到90%的车轴,最大速度为$ v _ {\ mathrm {max}} = 56,3〜 \ mathrm {m/s} $。分析表明,即使在实际操作条件下,我们开发的模型也可以使用加速度计作为VAD。
translated by 谷歌翻译