Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation
This work addresses generalization issues in vehicle routing for logistics and operations research, but it is incremental as it builds on existing knowledge distillation techniques.
The paper tackles the problem of poor cross-distribution generalization in neural methods for vehicle routing problems by proposing an Adaptive Multi-Distribution Knowledge Distillation (AMDKD) scheme, which achieves competitive results on both in-distribution and out-of-distribution instances while consuming less computational resources for inference.
Recent neural methods for vehicle routing problems always train and test the deep models on the same instance distribution (i.e., uniform). To tackle the consequent cross-distribution generalization concerns, we bring the knowledge distillation to this field and propose an Adaptive Multi-Distribution Knowledge Distillation (AMDKD) scheme for learning more generalizable deep models. Particularly, our AMDKD leverages various knowledge from multiple teachers trained on exemplar distributions to yield a light-weight yet generalist student model. Meanwhile, we equip AMDKD with an adaptive strategy that allows the student to concentrate on difficult distributions, so as to absorb hard-to-master knowledge more effectively. Extensive experimental results show that, compared with the baseline neural methods, our AMDKD is able to achieve competitive results on both unseen in-distribution and out-of-distribution instances, which are either randomly synthesized or adopted from benchmark datasets (i.e., TSPLIB and CVRPLIB). Notably, our AMDKD is generic, and consumes less computational resources for inference.