ML4CO-KIDA: Knowledge Inheritance in Dataset Aggregation
This work addresses a domain-specific problem for developers and researchers in combinatorial optimization, offering an incremental improvement over baseline methods.
The paper tackled the problem of improving combinatorial optimization solvers by replacing heuristic components with machine learning models, specifically for dual task branching decisions, and achieved first place in the NeurIPS 2021 ML4CO competition.
The Machine Learning for Combinatorial Optimization (ML4CO) NeurIPS 2021 competition aims to improve state-of-the-art combinatorial optimization solvers by replacing key heuristic components with machine learning models. On the dual task, we design models to make branching decisions to promote the dual bound increase faster. We propose a knowledge inheritance method to generalize knowledge of different models from the dataset aggregation process, named KIDA. Our improvement overcomes some defects of the baseline graph-neural-networks-based methods. Further, we won the $1$\textsuperscript{st} Place on the dual task. We hope this report can provide useful experience for developers and researchers. The code is available at https://github.com/megvii-research/NeurIPS2021-ML4CO-KIDA.