Coloring Big Graphs with AlphaGoZero

TL;DR

This paper introduces a novel deep reinforcement learning approach using AlphaGoZero techniques and a new neural network architecture, FastColorNet, to efficiently color large graphs, achieving state-of-the-art heuristics for an NP-hard problem.

Contribution

The paper presents a new neural network architecture and a reinforcement learning method that scales to large graphs and improves graph coloring heuristics without prior knowledge.

Findings

Achieved state-of-the-art heuristics for graph coloring

Developed FastColorNet with O(V) complexity for large graphs

Demonstrated effectiveness on real-world large graphs

Abstract

We show that recent innovations in deep reinforcement learning can effectively color very large graphs -- a well-known NP-hard problem with clear commercial applications. Because the Monte Carlo Tree Search with Upper Confidence Bound algorithm used in AlphaGoZero can improve the performance of a given heuristic, our approach allows deep neural networks trained using high performance computing (HPC) technologies to transform computation into improved heuristics with zero prior knowledge. Key to our approach is the introduction of a novel deep neural network architecture (FastColorNet) that has access to the full graph context and requires $O(V)$ time and space to color a graph with $V$ vertices, which enables scaling to very large graphs that arise in real applications like parallel computing, compilers, numerical solvers, and design automation, among others. As a result, we are able to learn new state of the art heuristics for graph coloring.