Pattern Recognition is the official journal of the Pattern Recognition Society. The Society was formed to fill a need for information exchange among research workers in the pattern recognition field. Up to now, we ''pattern-recognitionophiles'' have been tagging along in computer science, information theory, optical processing techniques, and other miscellaneous fields. Because this work in pattern recognition presently appears in widely spread articles and as isolated lectures in conferences in many diverse areas, the purpose of the journal Pattern Recognition is to give all of us an opportunity to get together in one place to publish our work. The journal will thereby expedite communication among research scientists interested in pattern recognition.

We consider pattern recognition in the broad sense, and we assume that the journal will be read by people with a common interest in pattern recognition but from many diverse backgrounds. These include biometrics, target recognition, biological taxonomy, meteorology, space science, classification methods, character recognition, image processing, industrial applications, neural computing, and many others.

The publication policy is to publish (1) new original articles that have been appropriately reviewed by competent scientific people, (2) reviews of developments in the field, and (3) pedagogical papers covering specific areas of interest in pattern recognition. Various special issues will be organized from time to time on current topics of interest to Pattern Recognition.

Special Issue on Machine Learning for Combinatorial Optimization and Its Applications (ML4CO)
Submission Date: 2021-04-01

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.