John R. Woodward

A Classification of Hyper-heuristic Approaches

The current state of the art in hyper-heuristic research comprises a set of approaches that share the common goal of automating the design and adaptation of heuristic methods to solve hard computational search problems. The main goal is to produce more generally applicable search methodologies. In this chapter we present an overview of previous categorisations of hyper-heuristics and provide a unified classification and definition, which capture the work that is being undertaken in this field. We distinguish between two main hyper-heuristic categories: heuristic selection and heuristic generation. Some representative examples of each category are discussed in detail. Our goals are to clarify the mainfeatures of existing techniques and to suggest new directions for hyper-heuristic research.

Exploring Hyper-heuristic Methodologies with Genetic Programming

Hyper-heuristics represent a novel search methodology that is motivated by the goal of automating the process of selecting or combining simpler heuristics in order to solve hard computational search problems. An extension of the original hyper-heuristic idea is to generate new heuristics which are not currently known. These approaches operate on a search space of heuristics rather than directly on a search space of solutions to the underlying problem which is the case with most meta-heuristics implementations. In the majority of hyper-heuristic studies so far, a framework is provided with a set of human designed heuristics, taken from the literature, and with good measures of performance in practice. A less well studied approach aims to generate new heuristics from a set of potential heuristic components. The purpose of this chapter is to discuss this class of hyper-heuristics, in which Genetic Programming is the most widely used methodology. A detailed discussion is presented including the steps needed to apply this technique, some representative case studies, a literature review of related work, and a discussion of relevant issues. Our aim is to convey the exciting potential of this innovative approach for automating the heuristic design process.

Automatic heuristic generation with genetic programming: evolving a jack-of-all-trades or a master of one

It is possible to argue that online bin packing heuristics should be evaluated by using metrics based on their performance over the set of all bin packing problems, such as the worst case or average case performance. However, this method of assessing a heuristic would only be relevant to a user who employs the heuristic over a set of problems which is actually representative of the set of all possible bin packing problems. On the other hand, a real world user will often only deal with packing problems that are representative of a particular sub-set. Their piece sizes will all belong to a particular distribution. The contribution of this paper is to show that a Genetic Programming system can automate the process of heuristic generation and produce heuristics that are human-competitive over a range of sets of problems, or which excel on a particular sub-set. We also show that the choice of training instances is vital in the area of automatic heuristic generation, due to the trade-off between the performance and generality of the heuristics generated and their applicability to new problems.

A Genetic Programming Hyper-Heuristic Approach for Evolving 2-D Strip Packing Heuristics

We present a genetic programming (GP) system to evolve reusable heuristics for the 2-D strip packing problem. The evolved heuristics are constructive, and decide both which piece to pack next and where to place that piece, given the current partial solution. This paper contributes to a growing research area that represents a paradigm shift in search methodologies. Instead of using evolutionary computation to search a space of solutions, we employ it to search a space of heuristics for the problem. A key motivation is to investigate methods to automate the heuristic design process. It has been stated in the literature that humans are very good at identifying good building blocks for solution methods. However, the task of intelligently searching through all of the potential combinations of these components is better suited to a computer. With such tools at their disposal, heuristic designers are then free to commit more of their time to the creative process of determining good components, while the computer takes on some of the design process by intelligently combining these components. This paper shows that a GP hyper-heuristic can be employed to automatically generate human competitive heuristics in a very-well studied problem domain.

A personal route prediction system based on trajectory data mining

This paper presents a system where the personal route of a user is predicted using a probabilistic model built from the historical trajectory data. Route patterns are extracted from personal trajectory data using a novel mining algorithm, Continuous Route Pattern Mining (CRPM), which can tolerate different kinds of disturbance in trajectory data. Furthermore, a client-server architecture is employed which has the dual purpose of guaranteeing the privacy of personal data and greatly reducing the computational load on mobile devices. An evaluation using a corpus of trajectory data from 17 people demonstrates that CRPM can extract longer route patterns than current methods. Moreover, the average correct rate of one step prediction of our system is greater than 71%, and the average Levenshtein distance of continuous route prediction of our system is about 30% shorter than that of the Markov model based method.

Contrasting meta-learning and hyper-heuristic research: the role of evolutionary algorithms

The fields of machine meta-learning and hyper-heuristic optimisation have developed mostly independently of each other, although evolutionary algorithms (particularly genetic programming) have recently played an important role in the development of both fields. Recent work in both fields shares a common goal, that of automating as much of the algorithm design process as possible. In this paper we first provide a historical perspective on automated algorithm design, and then we discuss similarities and differences between meta-learning in the field of supervised machine learning (classification) and hyper-heuristics in the field of optimisation. This discussion focuses on the dimensions of the problem space, the algorithm space and the performance measure, as well as clarifying important issues related to different levels of automation and generality in both fields. We also discuss important research directions, challenges and foundational issues in meta-learning and hyper-heuristic research. It is important to emphasize that this paper is not a survey, as several surveys on the areas of meta-learning and hyper-heuristics (separately) have been previously published. The main contribution of the paper is to contrast meta-learning and hyper-heuristics methods and concepts, in order to promote awareness and cross-fertilisation of ideas across the (by and large, non-overlapping) different communities of meta-learning and hyper-heuristic researchers. We hope that this cross-fertilisation of ideas can inspire interesting new research in both fields and in the new emerging research area which consists of integrating those fields.

Automating the packing heuristic design process with genetic programming

The literature shows that one-, two-, and three-dimensional bin packing and knapsack packing are difficult problems in operational research. Many techniques, including exact, heuristic, and metaheuristic approaches, have been investigated to solve these problems and it is often not clear which method to use when presented with a new instance. This paper presents an approach which is motivated by the goal of building computer systems which can design heuristic methods. The overall aim is to explore the possibilities for automating the heuristic design process. We present a genetic programming system to automatically generate a good quality heuristic for each instance. It is not necessary to change the methodology depending on the problem type (one-, two-, or three-dimensional knapsack and bin packing problems), and it therefore has a level of generality unmatched by other systems in the literature. We carry out an extensive suite of experiments and compare with the best human designed heuristics in the literature. Note that our heuristic design methodology uses the same parameters for all the experiments. The contribution of this paper is to present a more general packing methodology than those currently available, and to show that, by using this methodology, it is possible for a computer system to design heuristics which are competitive with the human designed heuristics from the literature. This represents the first packing algorithm in the literature able to claim human competitive results in such a wide variety of packing domains.

A histogram-matching approach to the evolution of bin-packing strategies

We present a novel algorithm for the one- dimension offline bin packing problem with discrete item sizes based on the notion of matching the item-size histogram with the bin-gap histogram. The approach is controlled by a constructive heuristic function which decides how to prioritise items in order to minimise the difference between histograms. We evolve such a function using a form of linear register-based genetic programming system. We test our evolved heuristics and compare them with hand-designed ones, including the well- known best fit decreasing heuristic. The evolved heuristics are human-competitive, generally being able to outperform high- performance human-designed heuristics.

Searching the Hyper-heuristic Design Space

We extend a previous mathematical formulation of hyper-heuristics to reflect the emerging generalization of the concept. We show that this leads naturally to a recursive definition of hyper-heuristics and to a division of responsibility that is suggestive of a blackboard architecture, in which individual heuristics annotate a shared workspace with information that may also be exploited by other heuristics. Such a framework invites consideration of the kind of relaxations of the domain barrier that can be achieved without loss of generality. We give a concrete example of this architecture with an application to the 3-SAT domain that significantly improves on a related token-ring hyper-heuristic.

Modularity in genetic programming

Genetic Programming uses a tree based representation to express solutions to problems. Trees are constructed from a primitive set which consists of a function set and a terminal set. An extension to GP is the ability to define modules, which are in turn tree based representations defined in terms of the primitives. The most well known of these methods is Kozas Automatically Defined Functions. In this paper it is proved that for a given problem, the minimum number of nodes in the main tree plus the nodes in any modules is independent of the primitive set (up to an additive constant) and depends only on the function being expressed. This reduces the number of user defined parameters in the run and makes the inclusion of a hypothesis in the search space independent of the primitive set.