Graph Convolutional Policy for Solving Tree Decomposition via Reinforcement Learning Heuristics

10/18/2019
by   Taras Khakhulin, et al.
40

We propose a Reinforcement Learning based approach to approximately solve the Tree Decomposition (TD)problem. TD is a combinatorial problem, which is central to the analysis of graph minor structure and computational complexity, as well as in the algorithms of probabilistic inference, register allocation, and other practical tasks. Recently, it has been shown that combinatorial problems can be successively solved by learned heuristics. However, the majority of existing works do not address the question of the generalization of learning-based solutions. Our model is based on the graph convolution neural network (GCN) for learning graph representations. We show that the agent builton GCN and trained on a single graph using an Actor-Critic method can efficiently generalize to real-world TD problem instances. We establish that our method successfully generalizes from small graphs, where TD can be found by exact algorithms, to large instances of practical interest, while still having very low time-to-solution. On the other hand, the agent-based approach surpasses all greedy heuristics by the quality of the solution.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/08/2019

Learning Heuristics over Large Graphs via Deep Reinforcement Learning

In this paper, we propose a deep reinforcement learning framework called...
research
06/07/2021

Learning Combinatorial Node Labeling Algorithms

We present a graph neural network to learn graph coloring heuristics usi...
research
01/22/2019

On multi-robot search for a stationary object

Two variants of multi-robot search for a stationary object in a priori k...
research
12/19/2020

Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances

For the traveling salesman problem (TSP), the existing supervised learni...
research
03/06/2023

Rolling Horizon based Temporal Decomposition for the Offline Pickup and Delivery Problem with Time Windows

The offline pickup and delivery problem with time windows (PDPTW) is a c...
research
04/08/2021

Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning

We present a novel method for graph partitioning, based on reinforcement...
research
06/04/2019

An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem

This paper introduces a new learning-based approach for approximately so...

Please sign up or login with your details

Forgot password? Click here to reset