Machine Learning for Evolutionary Computation - for Vehicle Routing Problems (ML4VRP)
GECCO 2024 | 14-18 July - Melbourne, Australia.
Competition Website: https://sites.google.com/view/ml4vrp
------------------------------------------------------------------------------------------
Overview
This competition aims to serve as a vehicle to bring together the latest developments of machine learning-assisted evolutionary computation for vehicle routing problems (VRPs). Results of current relevant research contain a lot of rich knowledge in evolutionary computation, which is however often discarded or not further investigated. These include different features of the problem/solutions to inform or drive the evolution/optimisation, different settings/operators/heuristics in effective evolutionary algorithms, and findings/evaluations of the search/fitness space. These can all be collected and processed as data, serving an excellent new problem domain for the machine learning community to enhance evolutionary computation.
VRP variants of different difficulties provide an ideal testbed to enable performance comparison of machine learning-assisted computational optimisation. Fostering, reusing, and interpreting the rich knowledge building ML4VRP remains a challenge for researchers across disciplines, however, is highly rewarding to further advance human-designed evolutionary computation.
Following the success of the previous competition, we are launching the competition at the GECCO'24, proposing two tracks in VRP, i.e., CVRP and CVRPTW. Participants are required to submit descriptions of the developed algorithms and the solutions for the provided CVRP/CVRPTW instances. The submissions will be evaluated on randomly selected instances (from the provided instances) using an evaluator available in our GitHub repository<https://github.com/ML4VRP/ML4VRP2024> dedicated to this competition.
Submission Instructions
Participants in the ML4VRP Competition should submit the following by 13 June 2024 to Rong.Qu@nottingham.ac.uk<mailto:Rong.Qu@nottingham.ac.uk>:
1. A short description of 1) the machine learning (e.g. supervised or unsupervised learning, reinforcement learning, deep learning, etc.) which design, assist and enhance evolutionary algorithms; 2) the resulting algorithms (e.g. meta-heuristics, evolutionary algorithms, etc.) supported by the machine learning for solving the CVRP/CVRPTW.
2. The solutions in the required format and the corresponding CVRP/CVRPTW instances, to be verified by the solution evaluator provided in the competition's GitHub repository.
Participants could also submit a two-page abstract by 8 April 2024, to be included in the GECCO proceedings if accepted. Please refer to the Information for authors of "2-page Competition Abstracts" at https://gecco-2024.sigevo.org/Paper-Submission-Instructions
Participants are also invited to submit a full paper to a special issue on ML4VRP in a journal. Details will be made available at the competition website as soon as the dates are agreed. We also encourage participants to attend GECCO 2024.
Important Dates
* Two-page abstract submission: 8 April 2024
* Description and solution submission: 13 June 2024
* GECCO 2024 Conference: 14-18 July 2024
Organisers
* Rong Qu, University of Nottingham, UK, rong.qu@nottingham.ac.uk<mailto:rong.qu@nottingham.ac.uk>
* Nelishia Pillay, University of Pretoria, South Africa, nelishia.pillay@up.ac.za<mailto:nelishia.pillay@up.ac.za>
* Weiyao Meng, University of Nottingham, UK, weiyao.meng2@nottingham.ac.uk<mailto:weiyao.meng2@nottingham.ac.uk>
This message and any attachment are intended solely for the addressee and may contain confidential information. If you have received this message in error, please contact the sender and delete the email and attachment. Any views or opinions expressed by the author of this email do not necessarily reflect the views of the University of Nottingham. Email communications with the University of Nottingham may be monitored where permitted by law.
**********************************************************
*
* Contributions to be spread via DMANET are submitted to
*
* DMANET@zpr.uni-koeln.de
*
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.
*
* DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET)
* http://www.zaik.uni-koeln.de/AFS/publications/dmanet/
*
**********************************************************
Posts
