Portrait of Quentin Cappart

Quentin Cappart

Affiliate Member
Associate Professor, Polytechnique Montréal, Department of Computer Engineering and Software Engineering
Research Topics
Graph Neural Networks
Learning on Graphs
Reasoning
Website
Google Scholar
LinkedIn
X

Biography

Quentin Cappart is an associate professor in the Department of Computer and Software Engineering at Polytechnique Montréal and an Affiliate member at Mila. He leads the CORAIL research group, which he co-founded with Louis-Martin Rousseau. Cappart obtained a BSc in engineering (2012), a MSc in computer engineering (2014), a MSc in management (2018) and a PhD (2017) at the Université catholique de Louvain (Belgium).

After his PhD, he joined Polytechnique Montréal and the International Research Centre on Enterprise Networks, Logistics and Transportation (CIRRELT) as a postdoctoral fellow (2018–2020). During these two years, he was also a research intern at ElementAI. Cappart’s main research area is the integration of machine learning with search procedures for solving combinatorial problems.

Current Students

Léo Boisvert
PhD - Polytechnique Montréal
Principal supervisor :
Alexandre Drouin
Francesco Morri
Postdoctorate - Polytechnique Montréal
Principal supervisor :
Margarida Carvalho
Website
Github
Google Scholar

Publications

The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights
Maxime Gasse
Quentin Cappart
Jonas Charfreitag
Laurent Charlin
Didier Chételat
Antonia Chmiela
Justin Dumouchelle
Ambros Gleixner
Aleksandr M. Kazachkov
Elias Khalil
Pawel Lichocki
Andrea Lodi
Miles Lubin
Chris J. Maddison
Christopher Morris
Dimitri J. Papageorgiou
Augustin Parjadis
Sebastian Pokutta
Antoine Prouvost
Lara Scavuzzo … (see 21 more)
Giulia Zarpellon
Linxin Yang
Sha Lai
Akang Wang
Xiaodong Luo
Xiang Zhou
Haohan Huang
Shengcheng Shao
Yuanming Zhu
Dong Zhang
Tao Quan
Zixuan Cao
Yang Xu
Zhewei Huang
Shuchang Zhou
Chen Binbin
He Minggui
Hao Hao
Zhang Zhiyu
An Zhiwu
Mao Kun
Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused … (see more)on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning as a new approach for solving combinatorial problems, either directly as solvers or by enhancing exact solvers. Based on this context, the ML4CO aims at improving state-of-the-art combinatorial optimization solvers by replacing key heuristic components. The competition featured three challenging tasks: finding the best feasible solution, producing the tightest optimality certificate, and giving an appropriate solver configuration. Three realistic datasets were considered: balanced item placement, workload apportionment, and maritime inventory routing. This last dataset was kept anonymous for the contestants.
2020-12-31
NeurIPS (Competition and Demos) (published)
doi.org
proceedings.mlr.press