Self-Evaluation for Job-Shop Scheduling
This addresses computationally intractable NP-hard scheduling problems for industries like manufacturing and logistics, representing an incremental improvement over existing neural optimization methods.
The paper tackles the error accumulation problem in neural combinatorial optimization for job-shop scheduling by proposing a self-evaluation framework that generates and evaluates subsets of assignments, surpassing state-of-the-art methods on challenging benchmarks.
Combinatorial optimization problems, such as scheduling and route planning, are crucial in various industries but are computationally intractable due to their NP-hard nature. Neural Combinatorial Optimization methods leverage machine learning to address these challenges but often depend on sequential decision-making, which is prone to error accumulation as small mistakes propagate throughout the process. Inspired by self-evaluation techniques in Large Language Models, we propose a novel framework that generates and evaluates subsets of assignments, moving beyond traditional stepwise approaches. Applied to the Job-Shop Scheduling Problem, our method integrates a heterogeneous graph neural network with a Transformer to build a policy model and a self-evaluation function. Experimental validation on challenging, well-known benchmarks demonstrates the effectiveness of our approach, surpassing state-of-the-art methods.