Machine Learning for Combinatorial Optimization and Its Applications (ML4CO)

The special issue will focus on the recent advance in learning to solve the combinatorial optimization problem, especially for problems related to pattern recognition. The capability of efficiently solving the challenging combinatorial optimization tasks, which are often NP-hard, is key to success of many business areas, ranging from transportation, aerospace industry, to industrial engineering etc. However, the traditional solvers are often based on rules and specific design based on human knowledge and experience, and the computing is often iterative and serialized on CPU, suffering limitation in scalability, adaptation ability, speed and accuracy.

The recent years have witnessed the rapid expansion of the frontier of using machine learning to solve the combinatorial optimization problems, and the related technologies vary from deep neural networks, reinforcement learning to decision tree models, especially given large amount of training data. Although the combinatorial optimization learning problem has been actively studied across different communities including pattern recognition, machine learning, computer vision, and algorithm etc. while there are still a large number of open problems for further study. In particular, the combination of big data and the deep learning paradigm has achieved significant success in many perceptual tasks. However, the existing paradigm is still far from a panacea to the combinatorial problem, which relates closely to decision-making. Also, there are emerging methods which can be more sample-efficient and scalable to large-scale problems.

This special issue will feature original research related to models and algorithms for combinatorial optimization based on machine learning or for machine learning itself, together with applications to real-world problems.

Main Topics of Interest (but not limited to):

• Learning techniques for combinatorial optimization (CO) problems: 1) Deep neural networks for CO; 2) Reinforcement learning for CO; 3) Decision tree-like learning methods for CO; 4); Multi-agent learning for CO; 5) Structured learning for CO; 6) Meta learning and transfer learning for CO; 7) Multi-task learning for CO; 8) Brain-inspired learning methods for CO; 8) Unsupervised learning for CO; 9) Traditional learning algorithms for CO and others.

• Combinatorial optimization for machine learning and AI: 1) Logic reasoning and rule discovery; 2) Optimal decision-making oriented prediction; 3) AutoML, discrete hyperparameter optimization, and network architecture search (NAS); 4) CO inspired machine learning methods.

• Applications: Application of learning based combinatorial optimization methods to solve any real-world optimization and decision-making problems including but not limited to: scheduling, planning, matching, routing, etc., especially in the uncertain and dynamic environments. The various applications areas are also welcomed, including but not limited to: EDA design, bioinformatics, transportation, industrial engineering, and drug molecular design, etc.

Key Deadlines/dates:

Submission period: January 1 – April 1, 2021

Final notice of acceptance/rejection: March 1, 2022

Guest Editors:

Junchi Yan (Managing GE)

Shanghai Jiao Tong University, China

Email: yanjunchi@sjtu.edu.cn

Zengfeng Huang

Fudan University, China

Email: huangzf@fudan.edu.cn

Wei Liu

Tencent AI Lab, China

Email: wliu@ee.columbia.edu

Jun Wang

University College London, UK

Email: jun.wang@cs.ucl.ac.uk

Hongyuan Zha

Georgia Institute of Technology, USA

Email: zha@cc.gatech.edu