Constraint Reasoning Embedded Structured Prediction
Constraint Reasoning Embedded Structured Prediction
复制标题
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Nan Jiang;Maosen Zhang;W. V. Hoeve;Yexiang Xue
中科院分区：
文献类型：
--
作者：
Nan Jiang;Maosen Zhang;W. V. Hoeve;Yexiang Xue
许多现实世界的结构化预测问题需要机器学习来捕捉数据分布和约束推理来确保结构的有效性。然而，由于缺乏连接约束满足和机器学习的工具，约束结构化预测在现实世界的应用中仍然受到限制。在本文中，我们提出了约束推理嵌入式S结构化预测（Core-Sp），一个可扩展的约束推理和机器学习集成的方法学习结构化领域。我们建议将决策图（一种流行的约束推理工具）作为一个完全可区分的模块嵌入深度神经网络中进行结构化预测。我们还提出了一个迭代搜索算法，自动搜索过程中的最佳核心SP结构。我们评估核心SP三个应用程序：车辆调度服务规划，如果，然后程序合成，和text 2SQL生成。所提出的核心-SP模块在所有三个应用程序中表现出比最先进的方法更优越的上级性能。当使用精确决策图时，使用Core-Sp生成的结构满足100%的约束。此外，Core-Sp通过约束满足减少建模空间来提高学习性能。
Many real-world structured prediction problems need machine learning to capture data distribution and constraint reasoning to ensure structure validity. Nevertheless, constrained structured prediction is still limited in real-world applications because of the lack of tools to bridge constraint satisfaction and machine learning. In this paper, we propose CO nstraint RE asoning embedded S tructured P rediction ( Core-Sp ), a scalable constraint reasoning and machine learning integrated approach for learning over structured domains. We propose to embed decision diagrams, a popular constraint reasoning tool, as a fully-differentiable module into deep neural networks for structured prediction. We also propose an iterative search algorithm to automate the searching process of the best Core-Sp structure. We evaluate Core-Sp on three applications: vehicle dispatching service planning, if-then program synthesis, and text2SQL generation. The proposed Core-Sp module demonstrates superior performance over state-of-the-art approaches in all three applications. The structures generated with Core-Sp satisfy 100% of the constraints when using exact decision diagrams. In addition, Core-Sp boosts learning performance by reducing the modeling space via constraint satisfaction.