Dock-based bike-sharing systems exhibit spatial imbalances between bicycle supply and user demand, often addressed through overnight truck-based rebalancing. This work studies static overnight rebalancing under demand uncertainty modeled as a tri-objective optimization problem. The objectives minimize total travel distance, expected unmet demand, and a robustness-oriented unmet demand measure over high-demand scenarios. Route plans are evaluated via a recourse simulation that enforces truck loads and station capacity constraints across multiple demand realizations. The robustness objective supports selecting plans that reduce peak-demand service degradation. Trade-off solutions are approximated with Non-dominated Sorting Genetic Algorithm II using a permutation-partition encoding and domain-specific relocation operators, including a biased best-improvement move for station relocation. Experiments on the real Barcelona Bicing system with 460 stations show well-distributed Pareto sets and substantial contributions to the reference non-dominated set. Greedy constructive baselines mainly yield extreme solutions and are often dominated.

This paper studies semi-supervised tabular classification in the extreme low-label regime using lightweight base learners. The paper proposes a cooperative coevolutionary method (CC-SSL) that evolves (i) two feature-subset views and (ii) a pseudo-labeling policy, and compares it to a matched monolithic evolutionary baseline (EA-SSL) and three lightweight SSL baselines. Experiments on 25 OpenML datasets with labeled fractions {1%, 5%, 10%} evaluate test MacroF1 and accuracy, together with evolutionary and pseudo-label diagnostics. CC-SSL and EA-SSL achieve higher median test MacroF1 than the lightweight baselines, with the largest separations at 1% labeled data. Most CC-SSL vs. EA-SSL comparisons are statistical draws on final test performance. EA-SSL shows higher best-so-far fitness and higher diversity during search, while time-to-target is comparable and generations-to-target favors EA-SSL in several multiclass settings. Pseudo-label volume, ProbeDrop, and validation optimism show no significant differences between CC-SSL and EA-SSL under the shared protocol.

Coevolutionary algorithms are a family of black-box optimisation algorithms with many applications in game theory. We study a coevolutionary algorithm on an important class of games in game theory: potential games. In these games, a real-valued function defined over the entire strategy space encapsulates the strategic choices of all players collectively. We present the first theoretical analysis of a coevolutionary algorithm on potential games, showing a runtime guarantee that holds for all exact potential games, some weighted and ordinal potential games, and certain non-potential games. Using this result, we show a polynomial runtime on singleton congestion games. Furthermore, we show that there exist games for which coevolutionary algorithms find Nash equilibria exponentially faster than best or better response dynamics, and games for which coevolutionary algorithms find better Nash equilibria as well. Finally, we conduct experimental evaluations showing that our algorithm can outperform widely used algorithms, such as better response on random instances of singleton congestion games, as well as fictitious play, counterfactual regret minimisation (CFR), and external sampling CFR on dynamic routing games.

This study explores a novel approach to neural network pruning using evolutionary computation, focusing on simultaneously pruning the encoder and decoder of an autoencoder. We introduce two new mutation operators that use layer activations to guide weight pruning. Our findings reveal that one of these activation-informed operators outperforms random pruning, resulting in more efficient autoencoders with comparable performance to canonically trained models. Prior work has established that autoencoder training is effective and scalable with a spatial coevolutionary algorithm that cooperatively coevolves a population of encoders with a population of decoders, rather than one autoencoder. We evaluate how the same activity-guided mutation operators transfer to this context. We find that random pruning is better than guided pruning, in the coevolutionary setting. This suggests activation-based guidance proves more effective in low-dimensional pruning environments, where constrained sample spaces can lead to deviations from true uniformity in randomization. Conversely, population-driven strategies enhance robustness by expanding the total pruning dimensionality, achieving statistically uniform randomness that better preserves system dynamics. We experiment with pruning according to different schedules and present best combinations of operator and schedule for the canonical and coevolving populations cases.

Image classification currently faces significant security challenges due to adversarial attacks, which consist of intentional alterations designed to deceive classification models based on artificial intelligence. This article explores an approach to generate adversarial attacks against image classifiers using a combination of evolutionary algorithms and generative adversarial networks. The proposed approach explores the latent space of a generative adversarial network with an evolutionary algorithm to find vectors representing adversarial attacks. The approach was evaluated in two case studies corresponding to the classification of handwritten digits and object images. The results showed success rates of up to 35% for handwritten digits, and up to 75% for object images, improving over other search methods and reported results in related works. The applied method proved to be effective in handling data diversity on the target datasets, even in problem instances that presented additional challenges due to the complexity and richness of information.

Electric vehicles (EVs) are establishing themselves as the mobility of the future. However, it requires an infrastructure, i.e., charging stations, still needs to adapt to the growing demand. This article presents a multi-objective approach to placing EV charging stations (EVCS) in urban areas. Our study takes into account both the quality of service to the citizens and the cost associated with the installation of charging stations. We have considered multiple types of EVCS, which will have different uses depending on the types of drivers. Also, our study integrates citizens' daily mobility patterns and residential locations. We used three multi-objective metaheuristics, NSGA-II, SPEA2, and MOEA/D, and evaluated them in a real-world case study in Malaga, Spain. Results indicated that NSGA-II and SPEA2 provide both competitive solutions, highlighting their effectiveness in balancing service quality and installation costs. This enhanced approach captures the dynamic aspects of citizens' daily and residential locations, offering nuanced insights into the electric vehicle charging station location problem.

Coevolutionary algorithms are helpful computational abstractions of adversarial behavior and they demonstrate multiple ways that populations of competing adversaries influence one another. We introduce the ability for each competitor's mutation rate to evolve through self-adaptation. Because dynamic environments are frequently addressed with self-adaptation, we set up dynamic problem environments to investigate the impact of this ability. For a simple bilinear problem, a sensitivity analysis of the adaptive method's parameters reveals that it is robust over a range of multiplicative rate factors, when the rate is changed up or down with equal probability. An empirical study determines that each population's mutation rates converge to values close to the error threshold. Mutation rate dynamics are complex when both populations adapt their rates. Large scale empirical self-adaptation results reveal that both reasonable solutions and rates can be found. This addresses the challenge of selecting ideal static mutation rates in coevolutionary algorithms. The algorithm's payoffs are also robust. They are rarely poor and frequently they are as high as the payoff of the static rate to which they converge. On rare runs, they are higher.

Training autoencoders is non-trivial. Convergence to the identity function or overfitting are common pitfalls. Population based algorithms like coevolutionary algorithms can provide diversity. To more robustly train autoencoders, we introduce a novel cooperative coevolutionary algorithm that exploits a spatial topology. We investigate the impact of algorithm parameters and design choices on the performance. On a simple tunable benchmark problem we observe that the performance can be improved over that of an conventionally trained autoencoder. However, the training convergence can be slow, despite the final model performance being competitive with a conventional autoencoder.

This paper proposes a multi-criteria approach to optimize urban infrastructure for e-scooters mobility. The problem considers redesigning road infrastructure to integrate e-scooters into a city's multimodal transportation system. This research aims to improve cycle lane coverage and connectivity for e-scooters while minimizing installation costs. Two parallel multi-objective evolutionary algorithms are devised to solve this problem in a real-world instance based on Málaga. The results showed that the algorithms effectively explored the Pareto front, offering diverse trade-off solutions. Key solutions are analyzed to evaluate the trade-offs between travel time improvement, cycle lane connectivity, multimodality, and installation costs. Visualization of proposed infrastructure changes illustrates significant reductions in travel time.

While competitive coevolutionary algorithms are ideally suited to model adversarial dynamics, their complexity makes it difficult to understand what is happening when they execute. To achieve better clarity, we introduce a game named DefendIt and explore a previously developed pairwise dominance coevolutionary algorithm named PDCoEA. We devise a methodology for consistent algorithm comparison, then use it to empirically study the impact of population size, the impact of relative budget limits between the defender and attacker, and the impact of mutation rates on the dynamics and payoffs. Our methodology provides reliable comparisons and records of run and multi-run dynamics. Our supplementary material also offers enticing and detailed animations of a pair of players' game moves over the course of a game of millions of moves matched to the same run's populations' payoffs.

It can be expensive to label images for classification. Good classifiers or high-quality images can be trained on unlabeled data with Generative Adversarial Network (GAN) methods. We use coevolutionary algorithms with Semi-Supervised GANs (SSL-GANs) that work with a few labeled and some more unlabeled images to train both a good classifier and a high-quality image generator. A spatial coevolutionary algorithm introduces diversity into the GAN training. We use a two-dimensional grid of GANs to gain discriminator loss diversity with a distributed cell-level coevolutionary algorithm. The GAN components are exchanged between neighboring cells based on performance and population-based hyperparameter tuning. The approach is demonstrated on two separate benchmark datasets, and with only a few labels, we simultaneously achieve good classification accuracy and high generated image quality score. In addition, the generated image quality and classification accuracy are competitive to state-of-the-art methods.

Medical image processing can lack images for diagnosis. Generative Adversarial Networks (GANs) provide a method to train generative models for data augmentation. Synthesized images can be used to improve the robustness of computer-aided diagnosis systems. However, GANs are difficult to train due to unstable training dynamics that may arise during the learning process, e.g., mode collapse and vanishing gradients. This paper focuses on Lipizzaner, a GAN training framework that combines spatial coevolution with gradient-based learning, which has been used to mitigate GAN training pathologies. Lipizzaner improves performance by taking advantage of its distributed nature and running at scale. Thus, the Lipizzaner algorithm and implementation robustness can be scaled to high-performance computing (HPC) systems to provide more accurate generative models. We address medical imaging data augmentation to create chest X-Ray images by using Lipizzaner on the HPC infrastructure provided by Oak Ridge National Labs' Summit Supercomputer. The experimental analysis shows improved performance by increasing the scale of the Lipizzaner GAN training. We also demonstrate that distributed coevolutionary learning improves performance even when using suboptimal neural network architectures due to hardware constraints.

Generative adversarial networks (GANs) exhibit training pathologies that can lead to convergence-related degenerative behaviors, whereas spatially-distributed, coevolutionary algorithms (CEAs) for GAN training, e.g. Lipizzaner, are empirically robust to them. The robustness arises from diversity that occurs by training populations of generators and discriminators in each cell of a toroidal grid. Communication, where signals in the form of parameters of the best GAN in a cell propagate in four directions: North, South, West and East, also plays a role, by communicating adaptations that are both new and fit. We propose Lipi-Ring, a distributed CEA like Lipizzaner, except that it uses a different spatial topology, i.e. a ring. Our central question is whether the different directionality of signal propagation (effectively migration to one or more neighbors on each side of a cell) meets or exceeds the performance quality and training efficiency of Lipizzaner. Experimental analysis on different datasets (i.e, MNIST, CelebA, and COVID-19 chest X-ray images) shows that there are no significant differences between the performances of the trained generative models by both methods. However, Lipi-Ring significantly reduces the computational time (14.2%... 41.2%). Thus, Lipi-Ring offers an alternative to Lipizzaner when the computational cost of training matters.

Generative Adversarial Networks (GANs) are difficult to train because of pathologies such as mode and discriminator collapse. Similar pathologies have been studied and addressed in competitive evolutionary computation by increased diversity. We study a system, Lipizzaner, that combines spatial coevolution with gradient-based learning to improve the robustness and scalability of GAN training. We study different features of Lipizzaner’s evolutionary computation methodology. Our ablation experiments determine that communication, selection, parameter optimization, and ensemble optimization each, as well as in combination, play critical roles. Lipizzaner succumbs less frequently to critical collapses and, as a side benefit, demonstrates improved performance. In addition, we show a GAN-training feature of Lipizzaner: the ability to train simultaneously with different loss functions in the gradient descent parameter learning framework of each GAN at each cell. We use an image generation problem to show that different loss function combinations result in models with better accuracy and more diversity in comparison to other existing evolutionary GAN models. Finally, Lipizzaner with multiple loss function options promotes the best model diversity while requiring a large grid size for adequate accuracy.

Generative Adversarial Networks (GANs) are popular tools for generative modeling. The dynamics of their adversarial learning give rise to convergence pathologies during training such as mode and discriminator collapse. In machine learning, ensembles of predictors demonstrate better results than a single predictor for many tasks. In this study, we apply two evolutionary algorithms (EAs) to create ensembles to re-purpose generative models, i.e., given a set of heterogeneous generators that were optimized for one objective (e.g., minimize Fréchet Inception Distance), create ensembles of them for optimizing a different objective (e.g., maximize the diversity of the generated samples). The first method is restricted by the exact size of the ensemble and the second method only restricts the upper bound of the ensemble size. Experimental analysis on the MNIST image benchmark demonstrates that both EA ensembles creation methods can re-purpose the models, without reducing their original functionality. The EA-based demonstrate significantly better performance compared to other heuristic-based methods. When comparing both evolutionary, the one with only an upper size bound on the ensemble size is the best.

Generative adversary networks (GANs) suffer from training pathologies such as instability and mode collapse. These pathologies mainly arise from a lack of diversity in their adversarial interactions. Evolutionary generative adversarial networks apply the principles of evolutionary computation to mitigate these problems. We hybridize two of these approaches that promote training diversity. One, E-GAN, at each batch, injects mutation diversity by training the (replicated) generator with three independent objective functions then selecting the resulting best performing generator for the next batch. The other, Lipizzaner, injects population diversity by training a two-dimensional grid of GANs with a distributed evolutionary algorithm that includes neighbor exchanges of additional training adversaries, performance based selection and population-based hyper-parameter tuning. We propose to combine mutation and population approaches to diversity improvement. We contribute a superior evolutionary GANs training method, Mustangs, that eliminates the single loss function used across Lipizzaner's grid. Instead, each training round, a loss function is selected with equal probability, from among the three E-GAN uses. Experimental analyses on standard benchmarks, MNIST and CelebA, demonstrate that Mustangs provides a statistically faster training method resulting in more accurate networks.

Internet is changing from an information space to a dynamic computing space. Data distribution and remotely accessible software services, dynamism, and autonomy are prime attributes. Cloud technology offers a powerful and fast growing approach to the provision of infrastructure (platform and software services) avoiding the high costs of owning, operating, and maintaining the computational infrastructures required for this purpose. Nevertheless, cloud technology still raises concerns regarding security, privacy, governance, and compliance of data and software services offered through it. Concerns are due to the difficulty to verify security properties of the different types of applications and services available through cloud technology, the uncertainty of their owners and users about the security of their services, and the applications based on them, once they are deployed and offered through a cloud. This work presents an innovative and novel evolution-oriented, cloud-specific monitoring model (including an architecture and a language) that aim at helping cloud application developers to design and monitor the behavior and functionality of their applications in a cloud environment.

This article describes the application of a multiobjective evolutionary algorithm for locating roadside infrastructure for vehicular communication networks over realistic urban areas. A multiobjective formulation of the problem is introduced, considering quality-of-service and cost objectives. The experimental analysis is performed over a real map of Málaga, using real traffic information and antennas, and scenarios that model different combinations of traffic patterns and applications (text/audio/video) in the communications. The proposed multiobjective evolutionary algorithm computes accurate trade-off solutions, significantly improving over state-of-the-art algorithms previously applied to the problem.

Vehicular ad hoc networks (VANETs) are infrastructure-less and self-organized networks deployed among vehicles and other road users. Due to the limitations of the wireless technologies used and the rapid topology changes, designing efficient routing protocols for VANETs is becoming a major concern. In this study, we applied a multi-objective optimization metaheuristic, in order to find efficient OLSR parameterizations that improve the QoS of the OLSR RFC and a previous optimized configurations. Our optimized configuration significantly reduces OLSR scalability problems keeping competitive packet delivery rates. The OLSR routing overhead is reduced between 47% and 76% and the delivery times are between 32% and 38% shorter when using our optimized settings.

Vehicular ad hoc networks (VANETs) provide the communications required to deploy Intelligent Transportation Systems (ITS). In the current state of the art in this field there is a lack of studies on real outdoor experiments to validate the new VANETs protocols and applications proposed by designers. In this work we have addressed the definition of a testbed in order to study the performance of the Vehicular Data Transfer Protocol (VDTP) in a real urban VANET. The VDTP protocol has been tested by employing six different parameter settings: one defined by human experts and five automatically optimized by means of metaheuristic algorithms (PSO, DE, GA, ES, and SA). As a result, we have been able to confirm the performance improvements when optimized VDTP configurations are used, validating the results previously obtained through simulation.