High-dimensional Unbalanced Binary Classification by Genetic Programming with Multi-criterion Fitness Evaluation and Selection

High-dimensional unbalanced classification is challenging because of the joint effects of high dimensionality and class imbalance. Genetic programming (GP) has the potential benefits for use in high-dimensional classification due to its built-in capability to select informative features. However, once data is not evenly distributed, GP tends to develop biased classifiers which achieve a high accuracy on the majority class but a low accuracy on the minority class. Unfortunately, the minority class is often at least as important as the majority class. It is of importance to investigate how GP can be effectively utilized for high-dimensional unbalanced classification. In this paper, to address the performance bias issue of GP, a new two-criterion fitness function is developed, which considers two criteria, i.e. the approximation of area under the curve (AUC) and the classification clarity (i.e. how well a program can separate two classes). The obtained values on the two criteria are combined in pairs, instead of summing them together. Furthermore, this paper designs a three-criterion tournament selection to effectively identify and select good programs to be used by genetic operators for generating better offspring during the evolutionary learning process. The experimental results show that the proposed method achieves better classification performance than other compared methods.

Dynastic Potential Crossover Operator

An optimal recombination operator for two parent solutions provides the best solution among those that take the value for each variable from one of the parents (gene transmission property). If the solutions are bit strings, the offspring of an optimal recombination operator is optimal in the smallest hyperplane containing the two parent solutions. Exploring this hyperplane is computationally costly, in general, requiring exponential time in the worst case. However, when the variable interaction graph of the objective function is sparse, exploration can be done in polynomial time. In this paper, we present a recombination operator, called Dynastic Potential Crossover (DPX), that runs in polynomial time and behaves like an optimal recombination operator for low-epistasis combinatorial problems. We compare this operator, both theoretically and experimentally, with traditional crossover operators, like uniform crossover and network crossover, and with two recently defined efficient recombination operators: partition crossover and articulation points partition crossover. The empirical comparison uses NKQ Landscapes and MAX-SAT instances. DPX outperforms the other crossover operators in terms of quality of the offspring and provides better results included in a trajectory and a population-based metaheuristic, but it requires more time and memory to compute the offspring.

Modular Grammatical Evolution for the Generation of Artificial Neural Networks

This paper presents a novel method, called Modular Grammatical Evolution (MGE), towards validating the hypothesis that restricting the solution space of NeuroEvolution to modular and simple neural networks enables the efficient generation of smaller and more structured neural networks while providing acceptable (and in some cases superior) accuracy on large data sets. MGE also enhances the state-of-the-art Grammatical Evolution (GE) methods in two directions. First, MGE's representation is modular in that each individual has a set of genes, and each gene is mapped to a neuron by grammatical rules. Second, the proposed representation mitigates two important drawbacks of GE, namely the low scalability and weak locality of representation, towards generating modular and multi-layer networks with a high number of neurons. We define and evaluate five different forms of structures with and without modularity using MGE and find single-layer modules with no coupling more productive. Our experiments demonstrate that modularity helps in finding better neural networks faster. We have validated the proposed method using ten well-known classification benchmarks with different sizes, feature counts, and output class counts. Our experimental results indicate that MGE provides superior accuracy with respect to existing NeuroEvolution methods and returns classifiers that are significantly simpler than other machine learning generated classifiers. Finally, we empirically demonstrate that MGE outperforms other GE methods in terms of locality and scalability properties.

Uncrowded Hypervolume-based Multi-objective Optimization with Gene-pool Optimal Mixing

Domination-based multi-objective (MO) evolutionary algorithms (EAs) are today arguably the most frequently used type of MOEA. These methods however stagnate when the majority of the population becomes non-dominated, preventing further convergence to the Pareto set. Hypervolume-based MO optimization has shown promising results to overcome this. Direct use of the hypervolume however results in no selection pressure for dominated solutions. The recently introduced Sofomore framework overcomes this by solving multiple interleaved single-objective dynamic problems that iteratively improve a single approximation set, based on the uncrowded hypervolume improvement (UHVI). It thereby however loses many advantages of population-based MO optimization, such as handling multimodality. Here, we reformulate the UHVI as a quality measure for approximation sets, called the uncrowded hypervolume (UHV), which can be used to directly solve MO optimization problems with a single-objective optimizer. We use the state-of-the-art gene-pool optimal mixing evolutionary algorithm (GOMEA) that is capable of efficiently exploiting the intrinsically available greybox properties of this problem. The resulting algorithm, UHV-GOMEA, is compared to Sofomore equipped with GOMEA, and the domination-based MO-GOMEA. In doing so, we investigate in which scenarios either domination-based or hypervolume-based methods are preferred. Finally, we construct a simple hybrid approach that combines MO-GOMEA with UHV-GOMEA and outperforms both.

Evolving Multimodal Robot Behavior via Many Stepping Stones with the Combinatorial Multi-Objective Evolutionary Algorithm

An important challenge in reinforcement learning is to solve multimodal problems, where agents have to act in qualitatively different ways depending on the circumstances. Because multimodal problems are often too difficult to solve directly, it is often helpful to define a curriculum, which is an ordered set of sub-tasks that can serve as the stepping stones for solving the overall problem. Unfortunately, choosing an effective ordering for these subtasks is difficult, and a poor ordering can reduce the performance of the learning process. Here, we provide a thorough introduction and investigation of the Combinatorial Multi-Objective Evolutionary Algorithm (CMOEA), which allows all combinations of subtasks to be explored simultaneously. We compare CMOEA against three algorithms that can similarly optimize on multiple subtasks simultaneously: NSGA-II, NSGA-III and ϵ-Lexicase Selection. The algorithms are tested on a function-optimization problem with two subtasks, a simulated multimodal robot locomotion problem with six subtasks and a simulated robot maze navigation problem where a hundred random mazes are treated as subtasks. On these problems, CMOEA either outperforms or is competitive with the controls. As a separate contribution, we show that adding a linear combination over all objectives can improve the ability of the control algorithms to solve these multimodal problems. Lastly, we show that CMOEA can leverage auxiliary objectives more effectively than the controls on the multimodal locomotion task. In general, our experiments suggest that CMOEA is a promising algorithm for solving multimodal problems.

An Analysis of the Influence of Non-effective Instructions in Linear Genetic Programming

Linear Genetic Programming (LGP) represents programs as sequences of instructions and has a Directed Acyclic Graph (DAG) dataflow. The results of instructions are stored in registers that can be used as arguments by other instructions. Instructions that are disconnected from the main part of the program are called non-effective instructions, or structural introns. They also appear in other DAG-based GP approaches like Cartesian Genetic Programming (CGP). This paper studies four hypotheses on the role of structural introns: non-effective instructions (1) serve as evolutionary memory, where evolved information is stored and later used in search, (2) preserve population diversity, (3) allow neutral search, where structural introns increase the number of neutral mutations and improve performance, and (4) serve as genetic material to enable program growth. We study different variants of LGP controlling the influence of introns for symbolic regression, classification, and digital circuits problems. We find that there is (1) evolved information in the non-effective instructions that can be reactivated and that (2) structural introns can promote programs with higher effective diversity. However, both effects have no influence on LGP search performance. On the other hand, allowing mutations to not only be applied to effective but also to noneffective instructions (3) increases the rate of neutral mutations and (4) contributes to program growth by making use of the genetic material available as structural introns. This comes along with a significant increase of LGP performance, which makes structural introns important for LGP.

Convergence Analysis of the Hessian Estimation Evolution Strategy

The class of algorithms called Hessian Estimation Evolution Strategies (HE-ESs) update the covariance matrix of their sampling distribution by directly estimating the curvature of the objective function. The approach is practically efficient, as attested by respectable performance on the BBOB testbed, even on rather irregular functions. In this paper we formally prove two strong guarantees for the (1+4)-HE-ES, a minimal elitist member of the family: stability of the covariance matrix update, and as a consequence, linear convergence on all convex quadratic problems at a rate that is independent of the problem instance.

Shape-constrained Symbolic Regression – Improving Extrapolation with Prior Knowledge

We investigate the addition of constraints on the function image and its derivatives for the incorporation of prior knowledge in symbolic regression. The approach is called shape-constrained symbolic regression and allows us to enforce e.g. monotonicity of the function over selected inputs. The aim is to find models which conform to expected behaviour and which have improved extrapolation capabilities. We demonstrate the feasibility of the idea and propose and compare two evolutionary algorithms for shapeconstrained symbolic regression: i) an extension of tree-based genetic programming which discards infeasible solutions in the selection step, and ii) a two population evolutionary algorithm that separates the feasible from the infeasible solutions. In both algorithms we use interval arithmetic to approximate bounds for models and their partial derivatives. The algorithms are tested on a set of 19 synthetic and four real-world regression problems. Both algorithms are able to identify models which conform to shape constraints which is not the case for the unmodified symbolic regression algorithms. However, the predictive accuracy of models with constraints is worse on the training set and the test set. Shape-constrained polynomial regression produces the best results for the test set but also significantly larger models.

Runtime Analysis of Restricted Tournament Selection for Bimodal Optimisation

Niching methods have been developed to maintain the population diversity, to investigate many peaks in parallel and to reduce the effect of genetic drift. We present the first rigorous runtime analyses of restricted tournament selection (RTS), embedded in a (μ+1) EA, and analyse its effectiveness at finding both optima of the bimodal function TwoMax. In RTS, an offspring competes against the closest individual, with respect to some distance measure, amongst w (window size) population members (chosen uniformly at random with replacement), to encourage competition within the same niche. We prove that RTS finds both optima on TwoMax efficiently if the window size w is large enough. However, if w is too small, RTS fails to find both optima even in exponential time, with high probability. We further consider a variant of RTS selecting individuals for the tournament without replacement. It yields a more diverse tournament and is more effective at preventing one niche from taking over the other. However, this comes at the expense of a slower progress towards optima when a niche collapses to a single individual. Our theoretical results are accompanied by experimental studies that shed light on parameters not covered by the theoretical results and support a conjectured lower runtime bound.

The Univariate Marginal Distribution Algorithm Copes Well With Deception and Epistasis

In their recent work, Lehre and Nguyen (FOGA 2019) show that the univariate marginal distribution algorithm (UMDA) needs time exponential in the parent populations size to optimize the DeceptiveLeadingBlocks (DLB) problem. They conclude from this result that univariate EDAs have difficulties with deception and epistasis. In this work, we show that this negative finding is caused by the choice of the parameters of the UMDA. When the population sizes are chosen large enough to prevent genetic drift, then the UMDA optimizes the DLB problem with high probability with at most λ(n2+2elnn) fitness evaluations. Since an offspring population size λ of order n log n can prevent genetic drift, the UMDA can solve the DLB problem with O(n2) log n fitness evaluations. In contrast, for classic evolutionary algorithms no better run time guarantee than O(n3) is known (which we prove to be tight for the (1 + 1) EA), so our result rather suggests that the UMDA can cope well with deception and epistatis. From a broader perspective, our result shows that the UMDA can cope better with local optima than many classic evolutionary algorithms; such a result was previously known only for the compact genetic algorithm. Together with the lower bound of Lehre and Nguyen, our result for the first time rigorously proves that running EDAs in the regime with genetic drift can lead to drastic performance losses.