Neural Large Neighborhood Search for the Capacitated Vehicle Routing Problem
This work addresses the challenge of improving automated heuristics for vehicle routing problems, which is incremental by integrating learned components into a traditional optimization framework.
The authors tackled the performance gap between machine learning and optimization methods for routing problems by proposing a neural large neighborhood search framework that integrates learned heuristics, achieving significant outperformance over handcrafted heuristics and existing machine learning approaches on capacitated and split delivery vehicle routing problems with up to 297 customers.
Learning how to automatically solve optimization problems has the potential to provide the next big leap in optimization technology. The performance of automatically learned heuristics on routing problems has been steadily improving in recent years, but approaches based purely on machine learning are still outperformed by state-of-the-art optimization methods. To close this performance gap, we propose a novel large neighborhood search (LNS) framework for vehicle routing that integrates learned heuristics for generating new solutions. The learning mechanism is based on a deep neural network with an attention mechanism and has been especially designed to be integrated into an LNS search setting. We evaluate our approach on the capacitated vehicle routing problem (CVRP) and the split delivery vehicle routing problem (SDVRP). On CVRP instances with up to 297 customers, our approach significantly outperforms an LNS that uses only handcrafted heuristics and a well-known heuristic from the literature. Furthermore, we show for the CVRP and the SDVRP that our approach surpasses the performance of existing machine learning approaches and comes close to the performance of state-of-the-art optimization approaches.