Structured Convolutional Kernel Networks for Airline Crew Scheduling

TL;DR

This paper introduces structured convolutional kernel networks (Struct-CKN) for airline crew scheduling, combining deep learning and kernel methods to improve large-scale crew pairing solutions with significant cost reductions.

Contribution

The paper develops a novel structured CKN framework that integrates constraints into the learning process for airline crew scheduling, enhancing solution quality.

Findings

Reduced crew pairing costs by 17% (millions of dollars)

Decreased global constraint costs by 97%

Achieved significant improvements over standard approaches

Abstract

Motivated by the needs from an airline crew scheduling application, we introduce structured convolutional kernel networks (Struct-CKN), which combine CKNs from Mairal et al. (2014) in a structured prediction framework that supports constraints on the outputs. CKNs are a particular kind of convolutional neural networks that approximate a kernel feature map on training data, thus combining properties of deep learning with the non-parametric flexibility of kernel methods. Extending CKNs to structured outputs allows us to obtain useful initial solutions on a flight-connection dataset that can be further refined by an airline crew scheduling solver. More specifically, we use a flight-based network modeled as a general conditional random field capable of incorporating local constraints in the learning process. Our experiments demonstrate that this approach yields significant improvements for the large-scale crew pairing problem (50,000 flights per month) over standard approaches, reducing the solution cost by 17% (a gain of millions of dollars) and the cost of global constraints by 97%.