On the Generalization of Neural Combinatorial Optimization Heuristics

by   Sahil Manchanda, et al.

Neural Combinatorial Optimization approaches have recently leveraged the expressiveness and flexibility of deep neural networks to learn efficient heuristics for hard Combinatorial Optimization (CO) problems. However, most of the current methods lack generalization: for a given CO problem, heuristics which are trained on instances with certain characteristics underperform when tested on instances with different characteristics. While some previous works have focused on varying the training instances properties, we postulate that a one-size-fit-all model is out of reach. Instead, we formalize solving a CO problem over a given instance distribution as a separate learning task and investigate meta-learning techniques to learn a model on a variety of tasks, in order to optimize its capacity to adapt to new tasks. Through extensive experiments, on two CO problems, using both synthetic and realistic instances, we show that our proposed meta-learning approach significantly improves the generalization of two state-of-the-art models.


Neural Combinatorial Optimization: a New Player in the Field

Neural Combinatorial Optimization attempts to learn good heuristics for ...

BQ-NCO: Bisimulation Quotienting for Generalizable Neural Combinatorial Optimization

Despite the success of Neural Combinatorial Optimization methods for end...

Unsupervised Learning for Combinatorial Optimization Needs Meta-Learning

A general framework of unsupervised learning for combinatorial optimizat...

Generalization of Machine Learning for Problem Reduction: A Case Study on Travelling Salesman Problems

Combinatorial optimization plays an important role in real-world problem...

Zero Training Overhead Portfolios for Learning to Solve Combinatorial Problems

There has been an increasing interest in harnessing deep learning to tac...

Learning to Optimise General TSP Instances

The Travelling Salesman Problem (TSP) is a classical combinatorial optim...

Simulation-guided Beam Search for Neural Combinatorial Optimization

Neural approaches for combinatorial optimization (CO) equip a learning m...

Please sign up or login with your details

Forgot password? Click here to reset