Multi-objective evolutionary algorithms (MOEAs) are widely used for searching optimal solutions in complex multi-component applications. Traditional MOEAs for multi-component deep learning (MCDL) systems face challenges in enhancing the search efficiency while maintaining the diversity. To combat these, this paper proposes $μ$MOEA, the first LLM-empowered adaptive evolutionary search algorithm to detect safety violations in MCDL systems. Inspired by the context-understanding ability of Large Language Models (LLMs), $μ$MOEA promotes the LLM to comprehend the optimization problem and generate an initial population tailed to evolutionary objectives. Subsequently, it employs adaptive selection and variation to iteratively produce offspring, balancing the evolutionary efficiency and diversity. During the evolutionary process, to navigate away from the local optima, $μ$MOEA integrates the evolutionary experience back into the LLM. This utilization harnesses the LLM's quantitative reasoning prowess to generate differential seeds, breaking away from current optimal solutions. We evaluate $μ$MOEA in finding safety violations of MCDL systems, and compare its performance with state-of-the-art MOEA methods. Experimental results show that $μ$MOEA can significantly improve the efficiency and diversity of the evolutionary search.
Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
Nanyang Technological University, Singapore（南洋理工大学）；The University of Hong Kong, Hong Kong, China（香港大学）；The Hong Kong Polytechnic University, Hong Kong, China（香港理工大学）；Zhejiang University, Zhejiang, China（浙江大学）；Renmin University of China, Beijing, China（中国人民大学）；Sun Yat-sen University, Guangdong, China（中山大学）；Northeastern University（东北大学）；Hebei Key Laboratory of Data Science and Knowledge Management（河北省数据科学与知识管理重点实验室）
LLM-Empowered Cooperative Content Caching in Vehicular Fog Caching-Assisted Platoon Networks
School of Internet of Things Engineering, Jiangnan University（江南大学物联网工程学院）；School of Information Engineering, Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications, Nanchang University（江西省级先进信号处理与智能通信重点实验室，南昌大学信息工程学院）；Department of Electronic Engineering, State Key Laboratory of Space Network and Communications, and the Beijing National Research Center for Information Science and Technology, Tsinghua University（电子工程系，空间网络与通信国家重点实验室，信息科学与技术国家研究中心，清华大学）；Department of Computer Science, Brunel University（计算机科学系，布鲁内尔大学）；State Key Laboratory of ISN and the School of Telecommunications Engineering, Xidian University（信息与通信国家重点实验室，西安电子科技大学电信工程学院）
From the evolution of public data ecosystems to the evolving horizons of the forward-looking intelligent public data ecosystem empowered by emerging technologies
University of Tartu（塔尔图大学）；University of Pardubice（帕尔杜比采大学）；University of Pristina – Kosovska Mitrovica（普里什蒂纳大学 – 科索夫斯卡米特罗维察）；University of Warsaw（华沙大学）；University of Granada（格拉纳达大学）
LLM-empowered Agents Simulation Framework for Scenario Generation in Service Ecosystem Governance
School of Software, Shandong University（软件学院，山东大学）；Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University（SDU-NTU人工智能研究中心（C-FAIR），山东大学）；College of Intelligence and Computing, Tianjin University（智能与计算学院，天津大学）；Tianjin Key Laboratory of Healthy Habitat and Smart Technology（天津健康人居环境与智能技术重点实验室）；Laboratory of Computation and Analytics of Complex Management Systems, Tianjin University（复杂管理系统计算与分析实验室，天津大学）；ShanDa Dareway Software Co. Ltd（山东达瑞软件有限公司）
Learning Evolution via Optimization Knowledge Adaptation
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education（教育部智能感知与图像理解重点实验室）；International Research Center for Intelligent Perception and Computation（智能感知与计算国际研究中心）；Xidian University（西安电子科技大学）
In this paper, a new method for assigning credit to search operators is presented. Starting with the principle of optimizing search bias, search operators are selected based on an ability to create solutions that are historically linked to future generations. Using a novel framework for defining performance measurements, distributing credit for performance, and the statistical interpretation of this credit, a new adaptive method is developed and shown to outperform a variety of adaptive and non-adaptive competitors.
School of Chemical Engineering（化工学院）；School of Information Technology（信息技术学院）；University of New South Wales（新南威尔士大学）；University of New South Wales and Electrical Engineering（新南威尔士大学与电气工程学院）
In this paper, the issue of adapting probabilities for Evolutionary Algorithm (EA) search operators is revisited. A framework is devised for distinguishing between measurements of performance and the interpretation of those measurements for purposes of adaptation. Several examples of measurements and statistical interpretations are provided. Probability value adaptation is tested using an EA with 10 search operators against 10 test problems with results indicating that both the type of measurement and its statistical interpretation play significant roles in EA performance. We also find that se…
The balance of exploration versus exploitation (EvE) is a key issue on evolutionary computation. In this paper we will investigate how an adaptive controller aimed to perform Operator Selection can be used to dynamically manage the EvE balance required by the search, showing that the search strategies determined by this control paradigm lead to an improvement of solution quality found by the evolutionary algorithm.
Online parameter controllers for evolutionary algorithms adjust values of parameters during the run of an evolutionary algorithm. Recently a new efficient parameter controller based on reinforcement learning was proposed by Karafotias et al. In this method ranges of parameters are discretized into several intervals before the run. However, performing adaptive discretization during the run may increase efficiency of an evolutionary algorithm. Aleti et al. proposed another efficient controller with adaptive discretization. In the present paper we propose a parameter controller based on reinforce…
Self-adaptive parameters are increasingly used in the field of Evolutionary Robotics, as they allow key evolutionary rates to vary autonomously in a context-sensitive manner throughout the optimisation process. A significant limitation to self-adaptive mutation is that rates can be set unfavourably, which hinders convergence. Rate restarts are typically employed to remedy this, but thus far have only been applied in Evolutionary Robotics for mutation-only algorithms. This paper focuses on the level at which evolutionary rate restarts are applied in population-based algorithms with more than 1 …
Large set of linear equations, especially for sparse and structured coefficient (matrix) equations, solutions using classical methods become arduous. And evolutionary algorithms have mostly been used to solve various optimization and learning problems. Recently, hybridization of classical methods (Jacobi method and Gauss-Seidel method) with evolutionary computation techniques have successfully been applied in linear equation solving. In the both above hybrid evolutionary methods, uniform adaptation (UA) techniques are used to adapt relaxation factor. In this paper, a new Jacobi Based Time-Vari…
The process of evolutionary emergence of purposeful adaptive behavior is investigated by means of computer simulations. The model proposed implies that there is an evolving population of simple agents, which have two natural needs: energy and reproduction. Any need is characterized quantitatively by a corresponding motivation. Motivations determine goal-directed behavior of agents. The model demonstrates that purposeful behavior does emerge in the simulated evolutionary processes. Emergence of purposefulness is accompanied by origin of a simple hierarchy in the control system of agents.
Coronavirus Optimization Algorithm: A Success-History Adaptive Evolutionary Framework with Archive-Assisted Search and Stagnation Recovery for Global Optimization
This paper proposes a hybrid self-adaptive evolutionary algorithm for graph coloring that is hybridized with the following novel elements: heuristic genotype-phenotype mapping, a swap local search heuristic, and a neutral survivor selection operator. This algorithm was compared with the evolutionary algorithm with the SAW method of Eiben et al., the Tabucol algorithm of Hertz and de Werra, and the hybrid evolutionary algorithm of Galinier and Hao. The performance of these algorithms were tested on a test suite consisting of randomly generated 3-colorable graphs of various structural features, …
Central South University（中南大学）；Hunan University（湖南大学）；South China University of Technology（华南理工大学）
The goal of constrained multiobjective evolutionary optimization is to obtain a set of well-converged and welldistributed feasible solutions. To complete this goal, there should be a tradeoff among feasibility, diversity, and convergence. However, it is nontrivial to balance these three elements simultaneously by using a single tradeoff model since the importance of each element varies in different evolutionary phases. As an alternative, we adapt different tradeoff models in different phases and propose a novel algorithm called ATM-R. In the infeasible phase, ATM-R takes the tradeoff between d…
Inspired by natural evolution, evolutionary search algorithms have proven remarkably capable due to their dual abilities to radiantly explore through diverse populations and to converge to adaptive pressures. A large part of this behavior comes from the selection function of an evolutionary algorithm, which is a metric for deciding which individuals survive to the next generation. In deceptive or hard-to-search fitness landscapes, greedy selection often fails, thus it is critical that selection functions strike the correct balance between gradient-exploiting adaptation and exploratory diversif…
The automatic generation of computer programs is one of the main applications with practical relevance in the field of evolutionary computation. With program synthesis techniques not only software developers could be supported in their everyday work but even users without any programming knowledge could be empowered to automate repetitive tasks and implement their own new functionality. In recent years, many novel program synthesis approaches based on evolutionary algorithms have been proposed and evaluated on common benchmark problems. Therefore, we identify in this work the relevant evolutio…
We present a novel approach for designing complex approximate arithmetic circuits that trade correctness for power consumption and play important role in many energy-aware applications. Our approach integrates in a unique way formal methods providing formal guarantees on the approximation error into an evolutionary circuit optimisation algorithm. The key idea is to employ a novel adaptive search strategy that drives the evolution towards promptly verifiable approximate circuits. As demonstrated in an extensive experimental evaluation including several structurally different arithmetic circuits…
Transfer Optimization is an incipient research area dedicated to solving multiple optimization tasks simultaneously. Among the different approaches that can address this problem effectively, Evolutionary Multitasking resorts to concepts from Evolutionary Computation to solve multiple problems within a single search process. In this paper we introduce a novel adaptive metaheuristic algorithm to deal with Evolutionary Multitasking environments coined as Adaptive Transfer-guided Multifactorial Cellular Genetic Algorithm (AT-MFCGA). AT-MFCGA relies on cellular automata to implement mechanisms in o…
A common claim of evolutionary computation methods is that they can achieve good results without the need for human intervention. However, one criticism of this is that there are still hyperparameters which must be tuned in order to achieve good performance. In this work, we propose a near "parameter-free" genetic programming approach, which adapts the hyperparameter values throughout evolution without ever needing to be specified manually. We apply this to the area of automated machine learning (by extending TPOT), to produce pipelines which can effectively be claimed to be free from human in…
he greatest weakness of evolutionary algorithms, widely used today, is the premature convergence due to the loss of population diversity over generations. To overcome this problem, several algorithms have been proposed, such as the Graph-based Evolutionary Algorithm (GEA) \cite{1} which uses graphs to model the structure of the population, but also memetic or differential evolution algorithms \cite{2,3}, or diversity-based ones \cite{4,5} have been designed. These algorithms are based on multi-populations, or often rather focus on the self-tuning parameters, however, they become complex to tun…
Allen Discovery Center at Tufts University（塔夫茨大学艾伦发现中心）；Institute for Theoretical Physics, TU Wien（维也纳技术大学理论物理研究所）；Wyss Institute for Biologically Inspired Engineering at Harvard University（哈佛大学威斯生物启发工程研究所）
Population-based evolutionary algorithms have great potential to handle multiobjective optimisation problems. However, these algorithms depends largely on problem characteristics, and there is a need to improve their performance for a wider range of problems. References, which are often specified by the decision maker's preference in different forms, are a very effective method to improve the performance of algorithms but have not been fully explored in literature. This paper proposes a novel framework for effective use of references to strengthen algorithms. This framework considers reference…
This paper presents the main characteristics of the evolutionary optimization code named EOS, Evolutionary Optimization at Sapienza, and its successful application to challenging, real-world space trajectory optimization problems. EOS is a global optimization algorithm for constrained and unconstrained problems of real-valued variables. It implements a number of improvements to the well-known Differential Evolution (DE) algorithm, namely, a self-adaptation of the control parameters, an epidemic mechanism, a clustering technique, an $\varepsilon$-constrained method to deal with nonlinear constr…
Robust Dynamic Material Handling via Adaptive Constrained Evolutionary Reinforcement Learning
Eindhoven University of Technology（埃因霍温理工大学）；Southern University of Science and Technology（南方科技大学）；Lingnan University（岭大大学）；Hong Kong Polytechnic University（香港理工大学）
Eindhoven University of Technology（埃因霍温理工大学）；Nobleo Manufacturing（Nobleo制造公司）
Multi-objective evolutionary algorithms (MOEAs) are widely used to solve multi-objective optimization problems. The algorithms rely on setting appropriate parameters to find good solutions. However, this parameter tuning could be very computationally expensive in solving non-trial (combinatorial) optimization problems. This paper proposes a framework that integrates MOEAs with adaptive parameter control using Deep Reinforcement Learning (DRL). The DRL policy is trained to adaptively set the values that dictate the intensity and probability of mutation for solutions during optimization. We test…
In the evolutionary computation research community, the performance of most evolutionary algorithms (EAs) depends strongly on their implemented coordinate system. However, the commonly used coordinate system is fixed and not well suited for different function landscapes, EAs thus might not search efficiently. To overcome this shortcoming, in this paper we propose a framework, named ACoS, to adaptively tune the coordinate systems in EAs. In ACoS, an Eigen coordinate system is established by making use of the cumulative population distribution information, which can be obtained based on a covari…
Building self-adaptive and self-organizing (SASO) systems is a challenging problem, in part because SASO principles are not yet well understood and few platforms exist for exploring them. Cellular automata (CA) are a well-studied approach to exploring the principles underlying self-organization. A CA comprises a lattice of cells whose states change over time based on a discrete update function. One challenge to developing CA is that the relationship of an update function, which describes the local behavior of each cell, to the global behavior of the entire CA is often unclear. As a result, man…
The major difficulty in Multi-objective Optimization Evolutionary Algorithms (MOEAs) is how to find an appropriate solution that is able to converge towards the true Pareto Front with high diversity. Most existing methodologies, which have demonstrated their niche on various practical problems involving two and three objectives, face significant challenges in the dependency of the selection of the EA parameters. Moreover, the process of setting such parameters is considered time-consuming, and several research works have tried to deal with this problem. This paper proposed a new Multi-objectiv…
The average convergence rate (ACR) measures how fast the approximation error of an evolutionary algorithm converges to zero per generation. It is defined as the geometric average of the reduction rate of the approximation error over consecutive generations. This paper makes a theoretical analysis of the ACR in continuous optimization. The obtained results are summarized as follows. According to the limit property, the ACR is classified into two categories: (1) linear ACR whose limit inferior value is larger than a positive and (2) sublinear ACR whose value converges to zero. Then, it is proven…
TECNALIA, Basque Research and Technology Alliance (BRTA)（TECNALIA，巴斯克研究与技术联盟（BRTA））；Universidad de Cantabria（坎塔布里亚大学）；Toho University（东邦大学）；University of the Basque Country (UPV/EHU)（巴斯克大学（UPV/EHU））
The emerging research paradigm coined as multitasking optimization aims to solve multiple optimization tasks concurrently by means of a single search process. For this purpose, the exploitation of complementarities among the tasks to be solved is crucial, which is often achieved via the transfer of genetic material, thereby forging the Transfer Optimization field. In this context, Evolutionary Multitasking addresses this paradigm by resorting to concepts from Evolutionary Computation. Within this specific branch, approaches such as the Multifactorial Evolutionary Algorithm (MFEA) has lately ga…
School of Engineering and Applied Science, Aston University（阿斯顿大学工程与应用科学学院）
This study suggests a new approach to EEG data classification by exploring the idea of using evolutionary computation to both select useful discriminative EEG features and optimise the topology of Artificial Neural Networks. An evolutionary algorithm is applied to select the most informative features from an initial set of 2550 EEG statistical features. Optimisation of a Multilayer Perceptron (MLP) is performed with an evolutionary approach before classification to estimate the best hyperparameters of the network. Deep learning and tuning with Long Short-Term Memory (LSTM) are also explored, a…
The Multi-Objective Real-Valued Gene-pool Optimal Mixing Evolutionary Algorithm (MO-RV-GOMEA) has been proven effective and efficient in solving real-world problems. A prime example is optimizing treatment plans for prostate cancer brachytherapy, an internal form of radiation treatment, for which equally important clinical aims from a base protocol are grouped into two objectives and bi-objectively optimized. This use of MO-RV-GOMEA was recently successfully introduced into clinical practice. Brachytherapy can also play an important role in treating cervical cancer. However, using the same app…
System identification is an exceptionally expansive topic and of remarkable significance in the discipline of signal processing and communication. Our goal in this paper is to show how simple adaptive FIR and IIR filters can be used in system modeling and demonstrating the application of adaptive system identification. The main objective of our research is to study the LMS algorithm and its improvement by the genetic search approach, namely, LMS-GA, to search the multi-modal error surface of the IIR filter to avoid local minima and finding the optimal weight vector when only measured or estima…
Multi-tasking optimization can usually achieve better performance than traditional single-tasking optimization through knowledge transfer between tasks. However, current multi-tasking optimization algorithms have some deficiencies. For high similarity problems, the knowledge that can accelerate the convergence rate of tasks has not been fully taken advantages of. For low similarity problems, the probability of generating negative transfer is high, which may result in optimization performance degradation. In addition, some knowledge transfer methods proposed previously do not fully consider how…
Hypergraph partitioning is an NP-hard problem that occurs in many computer science applications where it is necessary to reduce large problems into a number of smaller, computationally tractable sub-problems. Current techniques use a multilevel approach wherein an initial partitioning is performed after compressing the hypergraph to a predetermined level. This level is typically chosen to produce very coarse hypergraphs in which heuristic algorithms are fast and effective. This article presents a novel memetic algorithm which remains effective on larger initial hypergraphs. This enables the ex…
SONATA: Self-adaptive Evolutionary Framework for Hardware-aware Neural Architecture Search
LAMIH/UMR CNRS；Université Polytechnique Hauts-de-France（上法兰西理工大学）；University of Lille（里尔大学）；Centre de Recherche en Informatique Signal et Automatique de Lille (CRIStAL)（里尔信息、信号与自动化研究中心（CRIStAL））
We address a primary question of computational as well as biological research on evolution: How can an exploration strategy adapt in such a way as to exploit the information gained about the problem at hand? We first introduce an integrated formalism of evolutionary search which provides a unified view on different specific approaches. On this basis we discuss the implications of indirect modeling (via a ``genotype-phenotype mapping'') on the exploration strategy. Notions such as modularity, pleiotropy and functional phenotypic complex are discussed as implications. Then, rigorously reflecting…
Adaptive Protection for Evolutionary Feature Construction in Symbolic Regression with Application to Credit Classification
Centre for Data Science and Artificial Intelligence（数据科学与人工智能中心）；School of Engineering and Computer Science（工程与计算机科学学院）；Victoria University of Wellington（惠灵顿维多利亚大学）；Business School, Sichuan University（四川大学商学院）；Michigan State University（密歇根州立大学）
A fitness landscape is a genetic space -- with two genotypes adjacent if they differ in a single locus -- and a fitness function. Evolutionary dynamics produce a flow on this landscape from lower fitness to higher; reaching equilibrium only if a local fitness peak is found. I use computational complexity to question the common assumption that evolution on static fitness landscapes can quickly reach a local fitness peak. I do this by showing that the popular NK model of rugged fitness landscapes is PLS-complete for K >= 2; the reduction from Weighted 2SAT is a bijection on adaptive walks, so th…
In evolutionary computation, different reproduction operators have various search dynamics. To strike a well balance between exploration and exploitation, it is attractive to have an adaptive operator selection (AOS) mechanism that automatically chooses the most appropriate operator on the fly according to the current status. This paper proposes a new AOS mechanism for multi-objective evolutionary algorithm based on decomposition (MOEA/D). More specifically, the AOS is formulated as a multi-armed bandit problem where the dynamic Thompson sampling (DYTS) is applied to adapt the bandit learning …
The large number of exact fitness function evaluations makes evolutionary algorithms to have computational cost. In some real-world problems, reducing number of these evaluations is much more valuable even by increasing computational complexity and spending more time. To fulfill this target, we introduce an effective factor, in spite of applied factor in Adaptive Fuzzy Fitness Granulation with Non-dominated Sorting Genetic Algorithm-II, to filter out worthless individuals more precisely. Our proposed approach is compared with respect to Adaptive Fuzzy Fitness Granulation with Non-dominated Sor…
Differential evolution (DE) is a population based evolutionary algorithm widely used for solving multidimensional global optimization problems over continuous spaces. However, the design of its operators makes it unsuitable for many real-life constrained combinatorial optimization problems which operate on binary space. On the other hand, the quantum inspired evolutionary algorithm (QEA) is very well suitable for handling such problems by applying several quantum computing techniques such as Q-bit representation and rotation gate operator, etc. This paper extends the concept of differential op…
Large Language Models and Evolutionary Computation: A Critical Review of Bidirectional Interaction, Automated Algorithm Design, and Co-Adaptive Systems
Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学电气与计算机工程系）；Department of Computer Science, Universidad de Jaén（西班牙Jaén大学计算机科学系）；School of Computer and Mathematical Sciences, University of Adelaide（阿德莱德大学计算机与数学科学学院）；Leiden Institute of Advanced Computer Science, University Leiden（莱顿大学先进计算机科学研究所）；Department of Mathematics and Computing, Dr. B. R. Ambedkar National Institute of Technology（德拉·B·R·阿姆贝卡尔国立理工学院数学与计算系）
