Neural network pruning is a popular approach to reducing the computational complexity of deep neural networks. In recent years, as growing evidence shows that conventional network pruning methods employ inappropriate proxy metrics, and as new types of hardware become increasingly available, hardware-aware network pruning that incorporates hardware characteristics in the loop of network pruning has gained growing attention. Both network accuracy and hardware efficiency (latency, memory consumption, etc.) are critical objectives to the success of network pruning, but the conflict between the multiple objectives makes it impossible to find a single optimal solution. Previous studies mostly convert the hardware-aware network pruning to optimization problems with a single objective. In this paper, we propose to solve the hardware-aware network pruning problem with Multi-Objective Evolutionary Algorithms (MOEAs). Specifically, we formulate the problem as a multi-objective optimization problem, and propose a novel memetic MOEA, namely HAMP, that combines an efficient portfolio-based selection and a surrogate-assisted local search, to solve it. Empirical studies demonstrate the potential of MOEAs in providing simultaneously a set of alternative solutions and the superiority of HAMP compared to the state-of-the-art hardware-aware network pruning method.

Constrained many-objective optimization problems (CMaOPs) have gradually emerged in various areas and are significant for this field. These problems often involve intricate Pareto frontiers (PFs) that are both refined and uneven, thereby making their resolution difficult and challenging. Traditional algorithms tend to over prioritize convergence, leading to premature convergence of the decision variables, which greatly reduces the possibility of finding the constrained Pareto frontiers (CPFs). This results in poor overall performance. To tackle this challenge, our solution involves a novel dual-population constrained many-objective evolutionary algorithm based on reference point and angle easing strategy (dCMaOEA-RAE). It relies on a relaxed selection strategy utilizing reference points and angles to facilitate cooperation between dual populations by retaining solutions that may currently perform poorly but contribute positively to the overall optimization process. We are able to guide the population to move to the optimal feasible solution region in a timely manner in order to obtain a series of superior solutions can be obtained. Our proposed algorithm\'s competitiveness across all three evaluation indicators was demonstrated through experimental results conducted on 77 test problems. Comparisons with ten other cutting-edge algorithms further validated its efficacy.

BACKGROUND: Multimorbidity is a significant public health concern, characterized by the coexistence and interaction of multiple preexisting medical conditions. This complex condition has been associated with an increased risk of COVID-19. Individuals with multimorbidity who contract COVID-19 often face a significant reduction in life expectancy. The postpandemic period has also highlighted an increase in frailty, emphasizing the importance of integrating existing multimorbidity details into epidemiological risk assessments. Managing clinical data that include medical histories presents significant challenges, particularly due to the sparsity of data arising from the rarity of multimorbidity conditions. Also, the complex enumeration of combinatorial multimorbidity features introduces challenges associated with combinatorial explosions.
OBJECTIVE: This study aims to assess the severity of COVID-19 in individuals with multiple medical conditions, considering their demographic characteristics such as age and sex. We propose an evolutionary machine learning model designed to handle sparsity, analyzing preexisting multimorbidity profiles of patients hospitalized with COVID-19 based on their medical history. Our objective is to identify the optimal set of multimorbidity feature combinations strongly associated with COVID-19 severity. We also apply the Apriori algorithm to these evolutionarily derived predictive feature combinations to identify those with high support.
METHODS: We used data from 3 administrative sources in Piedmont, Italy, involving 12,793 individuals aged 45-74 years who tested positive for COVID-19 between February and May 2020. From their 5-year pre-COVID-19 medical histories, we extracted multimorbidity features, including drug prescriptions, disease diagnoses, sex, and age. Focusing on COVID-19 hospitalization, we segmented the data into 4 cohorts based on age and sex. Addressing data imbalance through random resampling, we compared various machine learning algorithms to identify the optimal classification model for our evolutionary approach. Using 5-fold cross-validation, we evaluated each model\'s performance. Our evolutionary algorithm, utilizing a deep learning classifier, generated prediction-based fitness scores to pinpoint multimorbidity combinations associated with COVID-19 hospitalization risk. Eventually, the Apriori algorithm was applied to identify frequent combinations with high support.
RESULTS: We identified multimorbidity predictors associated with COVID-19 hospitalization, indicating more severe COVID-19 outcomes. Frequently occurring morbidity features in the final evolved combinations were age>53, R03BA (glucocorticoid inhalants), and N03AX (other antiepileptics) in cohort 1; A10BA (biguanide or metformin) and N02BE (anilides) in cohort 2; N02AX (other opioids) and M04AA (preparations inhibiting uric acid production) in cohort 3; and G04CA (Alpha-adrenoreceptor antagonists) in cohort 4.
CONCLUSIONS: When combined with other multimorbidity features, even less prevalent medical conditions show associations with the outcome. This study provides insights beyond COVID-19, demonstrating how repurposed administrative data can be adapted and contribute to enhanced risk assessment for vulnerable populations.

Natural swimmers and flyers can fully recover from catastrophic propulsor damage by altering stroke mechanics: some fish can lose even 76% of their propulsive surface without loss of thrust. We consider applying these principles to enable robotic flapping propulsors to autonomously repair functionality. However, direct transference of these alterations from an organism to a robotic flapping propulsor may be suboptimal owing to irrelevant evolutionary pressures. Instead, we use machine learning techniques to compare these alterations with those optimal for a robotic system. We implement an online artificial evolution with hardware-in-the-loop, performing experimental evaluations with a flexible plate. To recoup thrust, the learned strategy increased amplitude, frequency and angle of attack (AOA) amplitude, and phase-shifted AOA by approximately 110°. Only amplitude increase is reported by most fish literature. When recovering side force, we find that force direction is correlated with AOA. No clear amplitude or frequency trend is found, whereas frequency increases in most insect literature. These results suggest that how mechanical flapping propulsors most efficiently adjust to damage may not align with natural swimmers and flyers.

As the fields of engineering, energy, and geology become increasingly complex, decision makers face escalating challenges that require skilled solutions to meet practical production needs. Evolutionary algorithms, inspired by biological evolution, have emerged as powerful methods for tackling intricate optimization problems without relying on gradient data. Among these, the tree-seed algorithm (TSA) distinguishes itself due to its unique mechanism and efficient searching capabilities. However, an imbalance between its exploitation and exploration phases can lead it to be stuck in local optima, impeding the discovery of globally optimal solutions. This study introduces an improved TSA that incorporates water-cycling and quantum rotation-gate mechanisms. These enhancements assist the algorithm in escaping local peaks and achieving a more harmonious balance between its exploitation and exploration phases. Comparative experimental evaluations, using the CEC 2017 benchmarks and a well-known metaheuristic algorithm, demonstrate the upgraded algorithm\'s faster convergence rate and enhanced ability to locate global optima. Additionally, its application in optimizing reservoir production models underscores its superior performance compared to competing methods, further validating its real-world optimization capabilities.

The besiege and conquer algorithm has shown excellent performance in single-objective optimization problems. However, there is no literature on the research of the BCA algorithm on multi-objective optimization problems. Therefore, this paper proposes a new multi-objective besiege and conquer algorithm to solve multi-objective optimization problems. The grid mechanism, archiving mechanism, and leader selection mechanism are integrated into the BCA to estimate the Pareto optimal solution and approach the Pareto optimal frontier. The proposed algorithm is tested with MOPSO, MOEA/D, and NSGAIII on the benchmark function IMOP and ZDT. The experiment results show that the proposed algorithm can obtain competitive results in terms of the accuracy of the Pareto optimal solution.

BACKGROUND: Drug design is a challenging and important task that requires the generation of novel and effective molecules that can bind to specific protein targets. Artificial intelligence algorithms have recently showed promising potential to expedite the drug design process. However, existing methods adopt multi-objective approaches which limits the number of objectives.
RESULTS: In this paper, we expand this thread of research from the many-objective perspective, by proposing a novel framework that integrates a latent Transformer-based model for molecular generation, with a drug design system that incorporates absorption, distribution, metabolism, excretion, and toxicity prediction, molecular docking, and many-objective metaheuristics. We compared the performance of two latent Transformer models (ReLSO and FragNet) on a molecular generation task and show that ReLSO outperforms FragNet in terms of reconstruction and latent space organization. We then explored six different many-objective metaheuristics based on evolutionary algorithms and particle swarm optimization on a drug design task involving potential drug candidates to human lysophosphatidic acid receptor 1, a cancer-related protein target.
CONCLUSIONS: We show that multi-objective evolutionary algorithm based on dominance and decomposition performs the best in terms of finding molecules that satisfy many objectives, such as high binding affinity and low toxicity, and high drug-likeness. Our framework demonstrates the potential of combining Transformers and many-objective computational intelligence for drug design.

The development of peptides for therapeutic targets or biomarkers for disease diagnosis is a challenging task in protein engineering. Current approaches are tedious, often time-consuming and require complex laboratory data due to the vast search spaces that need to be considered. In silico methods can accelerate research and substantially reduce costs. Evolutionary algorithms are a promising approach for exploring large search spaces and can facilitate the discovery of new peptides. This study presents the development and use of a new variant of the genetic-programming-based POET algorithm, called POET Regex , where individuals are represented by a list of regular expressions. This algorithm was trained on a small curated dataset and employed to generate new peptides improving the sensitivity of peptides in magnetic resonance imaging with chemical exchange saturation transfer (CEST). The resulting model achieves a performance gain of 20% over the initial POET models and is able to predict a candidate peptide with a 58% performance increase compared to the gold-standard peptide. By combining the power of genetic programming with the flexibility of regular expressions, new peptide targets were identified that improve the sensitivity of detection by CEST. This approach provides a promising research direction for the efficient identification of peptides with therapeutic or diagnostic potential.

We study the (1:s+1) success rule for controlling the population size of the (1,λ)- EA. It was shown by Hevia Fajardo and Sudholt that this parameter control mechanism can run into problems for large s if the fitness landscape is too easy. They conjectured that this problem is worst for the ONEMAX benchmark, since in some well-established sense ONEMAX is known to be the easiest fitness landscape. In this paper we disprove this conjecture. We show that there exist s and ɛ such that the self-adjusting (1,λ)-EA with the (1:s+1)-rule optimizes ONEMAX efficiently when started with ɛn zero-bits, but does not find the optimum in polynomial time on DYNAMIC BINVAL. Hence, we show that there are landscapes where the problem of the (1:s+1)-rule for controlling the population size of the (1,λ)-EA is more severe than for ONEMAX. The key insight is that, while ONEMAX is the easiest function for decreasing the distance to the optimum, it is not the easiest fitness landscape with respect to finding fitness-improving steps.

The fitness level method is a popular tool for analyzing the hitting time of elitist evolutionary algorithms. Its idea is to divide the search space into multiple fitness levels and estimate lower and upper bounds on the hitting time using transition probabilities between fitness levels. However, the lower bound generated by this method is often loose. An open question regarding the fitness level method is what are the tightest lower and upper time bounds that can be constructed based on transition probabilities between fitness levels. To answer this question, we combine drift analysis with fitness levels and define the tightest bound problem as a constrained multi-objective optimization problem subject to fitness levels. The tightest metric bounds by fitness levels are constructed and proven for the first time. Then linear bounds are derived from metric bounds and a framework is established that can be used to develop different fitness level methods for different types of linear bounds. The framework is generic and promising, as it can be used to draw tight time bounds on both fitness landscapes with and without shortcuts. This is demonstrated in the example of the (1+1) EA maximizing the TwoMax1 function.