Moco: A Learnable Meta Optimizer for Combinatorial Optimization
CoRR(2024)
摘要
Relevant combinatorial optimization problems (COPs) are often NP-hard. While
they have been tackled mainly via handcrafted heuristics in the past, advances
in neural networks have motivated the development of general methods to learn
heuristics from data. Many approaches utilize a neural network to directly
construct a solution, but are limited in further improving based on already
constructed solutions at inference time. Our approach, Moco, learns a graph
neural network that updates the solution construction procedure based on
features extracted from the current search state. This meta training procedure
targets the overall best solution found during the search procedure given
information such as the search budget. This allows Moco to adapt to varying
circumstances such as different computational budgets. Moco is a fully
learnable meta optimizer that does not utilize any problem specific local
search or decomposition. We test Moco on the Traveling Salesman Problem (TSP)
and Maximum Independent Set (MIS) and show that it outperforms other approaches
on MIS and is overall competitive on the TSP, especially outperforming related
approaches, partially even if they use additional local search.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要