论文标题
学习组合优化的可解释错误功能问题建模
Learning Interpretable Error Functions for Combinatorial Optimization Problem Modeling
论文作者
论文摘要
在约束编程中，通常将约束表示为允许或禁止值组合的谓词。但是，某些算法利用了更细的表示：错误函数。不过，它们的用法是有价值的：这使问题建模变得更加困难。在这里，我们提出了一种方法，可以自动学习与约束相对应的错误函数，给定确定分配是否有效的函数。据我们所知，这是自动学习错误函数的第一次尝试以实现硬性约束。我们的方法使用了一种神经网络的变体，我们将其命名为可解释的组成网络，从而使我们获得可解释的结果，与常规的人工神经网络不同。对5个不同约束的实验表明，我们的系统可以学习扩展到高维度的功能，并且可以在不完整的空间上学习相当好的功能。
In Constraint Programming, constraints are usually represented as predicates allowing or forbidding combinations of values. However, some algorithms exploit a finer representation: error functions. Their usage comes with a price though: it makes problem modeling significantly harder. Here, we propose a method to automatically learn an error function corresponding to a constraint, given a function deciding if assignments are valid or not. This is, to the best of our knowledge, the first attempt to automatically learn error functions for hard constraints. Our method uses a variant of neural networks we named Interpretable Compositional Networks, allowing us to get interpretable results, unlike regular artificial neural networks. Experiments on 5 different constraints show that our system can learn functions that scale to high dimensions, and can learn fairly good functions over incomplete spaces.
