Efficient Training of Multi-task Neural Solver for Combinatorial Optimization

Understand

Efficiently training a multi-task neural solver for various combinatorial optimization problems (COPs) has been less studied so far.

• Naive application of conventional multi-task learning approaches often falls short in delivering a high-quality, unified neural solver.
• This deficiency primarily stems from the significant computational demands and a lack of adequate consideration for the complexities inherent in COPs.
• In this paper, we propose a general and efficient training paradigm to deliver a unified combinatorial multi-task neural solver.