Timezone: »

 
Spotlight
Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation
Jieyi Bi · Yining Ma · Jiahai Wang · Zhiguang Cao · Jinbiao Chen · Yuan Sun · Yeow Meng Chee

Thu Dec 08 09:00 AM -- 11:00 AM (PST) @
in Lightning Talks 5B-3 »

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.

Keywords: Combinatorial Optimization · generalization · knowledge distillation · vehicle routing problem · learning to optimize

Author Information

Jieyi Bi (SUN YAT-SEN UNIVERSITY)
Yining Ma (National University of Singapore)
Jiahai Wang (SUN YAT-SEN UNIVERSITY)
Zhiguang Cao (Singapore Institute of Manufacturing Technology)
Jinbiao Chen (SUN YAT-SEN UNIVERSITY)
Yuan Sun (The University of Melbourne)
Yeow Meng Chee (National University of Singapore)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors