Learning Combinatorial Optimization Algorithms over Graphs 翻译

学习图组合优化算法

摘要

The design of good heuristics or approximation algorithms for NP-hard combinatorial optimization problems often requires significant specialized knowledge and trial-and-error. Can we automate this challenging, tedious process, and learn the algorithms instead? In many real-world applications, it is typically the case that the same optimization problem is solved again and again on a regular basis, maintaining the same problem structure but differing in the data. This provides an opportunity for learning heuristic algorithms that exploit the structure of such recurring problems. In this paper, we propose a unique combination of reinforcement learning and graph embedding to address this challenge. The learned greedy policy behaves like a meta-algorithm that incrementally constructs a solution, and the action is determined by the output of a graph embedding network capturing the current state of the solution. We show that our framework can be applied to a diverse range of optimization problems over graphs, and learns effective algorithms for the Minimum Vertex Cover, Maximum Cut and Traveling Salesman problems.

NP-hard组合优化问题的良好启发式或近似算法的设计通常需要大量的专业知识和反复试验。我们可以自动化这个具有挑战性的繁琐过程，并学习算法吗？在许多实际应用中，通常情况是，定期地一次又一次地解决相同的优化问题，保持相同的问题结构但数据不同。这为学习利用这种反复出现的问题的结构的启发式算法提供了机会。在本文中，我们提出了强化学习和图形嵌入的独特组合来应对这一挑战。学习贪婪策略的行为类似于逐步构建解决方案的元算法，并且动作由捕获解决方案当前状态的图形嵌入网络的输出确定。我们展示了我们的框架可以应用于图形上的各种优化问题，并学习最小顶点覆盖，最大切割和旅行推销员问题的有效算法。

简介