Metaheuristics for robust graph coloring

This paper studies a robust graph coloring problem, which is a variant of the classical graph coloring problem, where penalties are charged for non-adjacent vertices that are assigned the same color. The problem can be formulated as an unconstrained quadratic programming problem, and has many applications in industry. Since the problem is known to be strongly NP-complete, we develop a number of metaheuristics for it, which are based on various encoding schemes, neighborhood structures, and search algorithms. Extensive experiments suggest that our metaheuristics with a partition based encoding scheme and an improvement graph based neighborhood outperform other methods tested in our study.