Yaochu Jin

Westlake University · School of Engineering

Gaussian processes (GPs) are widely employed in surrogate-assisted evolutionary algorithms (SAEAs) because they can estimate the level of uncertainty in their predictions. However, the computational complexity of GPs grows cubically with the number of training samples, the time required for constructing a GP becomes excessively long. Additionally,...

Reinforcement learning methods have been used to optimize long-term user engagement in recommendation systems. However, existing reinforcement learning-based recommendation systems do not fully exploit the relevance of individual user behavior across different platforms. One potential solution is to aggregate data from various platforms in a centra...

Model-based reinforcement learning (MBRL) has shown its advantages in sample efficiency over model-free reinforcement learning (MFRL) by leveraging control-based domain knowledge. Despite the impressive results it achieves, MBRL is still outperformed by MFRL due to the lack of unlimited interactions with the environment. While imaginary data can be...

As a pivotal technique in intelligent education systems, cognitive diagnosis (CD) serves to reveal students' knowledge proficiency for better tackling subsequent tasks. Unfortunately, due to pursuing high model interpretability, existing manually designed models for CD often hold simplistic architectures, which cannot cope with intricate data in mo...

Recently, computationally intensive multiobjective optimization problems have been efficiently solved by surrogate-assisted multiobjective evolutionary algorithms. However, most of those algorithms can only handle no more than 200 decision variables. As the number of decision variables increases further, unreliable surrogate models will result in a...

Graph neural networks (GNNs) have emerged as a powerful tool for solving combinatorial optimization problems (COPs), exhibiting state-of-the-art performance in both graph-structured and non-graph-structured domains. However, existing approaches lack a unified framework capable of addressing a wide range of COPs. After presenting a summary of repres...

Binary optimization assumes a pervasive significance in the context of practical applications, such as knapsack problems, maximum cut problems, and critical node detection problems. Existing techniques including mathematical programming, heuristics, evolutionary computation, and neural networks have been employed to tackle binary optimization probl...

Gasoline blending scheduling uses resource allocation and operation sequencing to meet a refinery’s production requirements. The presence of nonlinearity, integer constraints, and a large number of decision variables adds complexity to this problem, posing challenges for traditional and evolutionary algorithms. This paper introduces a novel multiob...

Expensive constrained multi-objective optimization problems (ECMOPs) present a significant challenge to surrogate-assisted evolutionary algorithms (SAEAs) in effectively balancing optimization of the objectives and satisfaction of the constraints with complex landscapes, leading to low feasibility, poor convergence and insufficient diversity. To ad...

Image anomaly detection (IAD) is an emerging and vital computer vision task in industrial manufacturing (IM). Recently, many advanced algorithms have been reported, but their performance deviates considerably with various IM settings. We realize that the lack of a uniform IM benchmark is hindering the development and usage of IAD methods in real-wo...

The recent rapid development of deep learning has laid a milestone in industrial image anomaly detection (IAD). In this paper, we provide a comprehensive review of deep learning-based image anomaly detection techniques, from the perspectives of neural network architectures, levels of supervision, loss functions, metrics and datasets. In addition, w...

Cooperative co-evolution (CC) algorithms, based on the divide-and-conquer strategy, have emerged as the predominant approach to solving large-scale global optimization (LSGO) problems. The efficiency and accuracy of the grouping stage significantly impact the performance of the optimization process. While the general separability grouping (GSG) met...

In recent decades, various surrogate-assisted evolutionary algorithms (SAEAs) have been proposed to solve computationally expensive multiobjective optimization problems (EMOPs). Nevertheless, designing an SAEA to handle high-dimensional EMOPs and balance convergence, diversity, and computational complexity remains challenging. Here, we propose a tw...

Inspired by natural evolutionary processes, Evolutionary Computation (EC) has established itself as a cornerstone of Artificial Intelligence. Recently, with the surge in data-intensive applications and large-scale complex systems, the demand for scalable EC solutions has grown significantly. However, most existing EC infrastructures fall short of c...

Large-scale overlapping problems are prevalent in practical engineering applications, and the optimization challenge is significantly amplified due to the existence of shared variables. Decomposition-based cooperative coevolution (CC) algorithms have demonstrated promising performance in addressing large-scale overlapping problems. However, current...

Constrained multimodal multiobjective optimization problems (CMMOPs) are challenging in the field of optimization, requiring to consider the balance between the constraints and objectives, the balance between exploration and exploitation in the decision space and the objective space, and the balance of diversity between the decision space and the o...

In surrogate-assisted evolutionary optimization, privacy-preservation and trusted data sharing has become an increasingly important concern, especially in scenarios involving distributed sensitive data. Existing privacy-preserving surrogate-assisted evolutionary optimization algorithms heavily rely on the basic federated learning framework. However...

Surrogate-assisted evolutionary algorithms (SAEAs) rely on the infill criterion to select candidate solutions for expensive evaluations. However, in the context of expensive constrained multi-objective optimization problems (ECMOPs) with complex feasible regions, guiding the optimization algorithm towards the constrained Pareto optimal front and ac...

Gasoline blending scheduling is challenging, involving multiple conflicting objectives and a large decision space with many mixed integers. Due to these difficulties, one promising solution is to use preference-based multi-objective evolutionary algorithms (PBMOEAs). However, in practical applications, suitable preferences of decision makers are of...

In real-world applications, a specific class of multiobjective optimization problems, such as the cloud service allocation problem (CSAOPs), possess the characteristic of variable-length and mixed variables, termed as variable multiobjective optimization problems (VMMOPs). Unfortunately, little research has been reported to solve them. To fill the...

Building energy management usually involves a number of objectives, such as investment costs, thermal comfort, system resilience, battery life, and many others. However, most existing studies merely consider optimizing less than three objectives since it becomes increasingly difficult as the number of objectives increases. In addition, the optimiza...

Liquid state machines (LSMs) are biologically more plausible than feedforward spiking neural networks for brain-inspired computing and neuromorphic engineering. However, optimizing and training complex recurrent network architectures in the reservoir of LSMs remains challenging. Most existing algorithms aim to adjust the synaptic strength only, wit...

Optimization problems whose evaluations of the objective and constraints involve costly numerical simulations or physical experiments are referred to as expensive constrained optimization (ECO) problems. Such problems can be solved by evolutionary algorithms (EAs) in conjunction with computationally cheap surrogates that separately approximate the...

Machine learning plays an increasingly important role in the field of artificial intelligence, and obtains fantastic performance in various real-world applications, including image classification, computer vision, natural language processing, and recommendation systems, among many others. Meanwhile, in the era of Big Data, both security and privacy...

Despite that the surrogate-assisted evolutionary algorithms have achieved great success in addressing expensive optimization problems, they still suffer from stiff challenges when the number of dimensions of problems becomes large. The primary reason lies in that it is very hard to build an acceptable surrogate model in the high-dimensional search...

Multi-modality imaging improves disease diagnosis and reveals distinct deviations in tissues with anatomical properties. The existence of completely aligned and paired multi-modality neuroimaging data has proved its effectiveness in brain research. However, collecting fully aligned and paired data is expensive or even impractical, since it faces ma...

The purpose of this study was to develop an evolutionary algorithm (EA) with bilevel surrogate modeling, called BL-SAEA, for tackling bilevel optimization problems (BLOPs), in which an upper level problem is to be solved subject to the optimality of a corresponding lower level problem. The motivation of this article is that the extensive lower leve...

This article studies reliable shortest path (RSP) problems in stochastic transportation networks. The term reliability in the RSP literature has many definitions, e.g., 1) maximal stochastic on-time arrival probability, 2) minimal travel time with a high-confidence constraint, 3) minimal mean and standard deviation combination, and 4) minimal exp...

Many real-world optimization problems possess dynamic characteristics. Evolutionary dynamic optimization algorithms (EDOAs) aim to tackle the challenges associated with dynamic optimization problems. Looking at the existing works, the results reported for a given EDOA can sometimes be considerably different. This issue occurs because the source cod...

In recent years, solving constrained multiobjective optimization problems (CMOPs) by introducing simple helper problems has become a popular concept. To date, no systematic study has investigated the conditions under which this concept operates. In this study, we presented a holistic overview of existing constrained multiobjective evolutionary algo...

The complex network has attracted increasing attention and shown effectiveness in modeling multifarious systems. Focusing on selecting members with good spreading ability, the influence maximization problem is of great significance in network-based information diffusion tasks. Plenty of attention has been paid to simulating the diffusion process an...

Federated learning (FL) draws attention in academia and industry due to its privacy-preserving capability in training machine learning models. However, there are still some critical security attacks and vulnerabilities, including gradients leakage and interference attacks. Meanwhile, communication is another bottleneck in basic FL schemes since lar...

The insights and benefits to be realised through the optimisation of multiple independent, but conflicting objectives are well recognised by practitioners seeking effective and robust solutions to real-world application problems. Key issues encountered by users of many-objective optimisation (>3 objectives) in a real-world environment are discussed...

Chapter 4 presents a model for multi-cellular development by evolving the genetic network that controls the cellular growth process. The central point in this process is to make sure that the evolved gene regulatory network can generate a stable growth process that is able to achieve a balance between cell division and cell apoptosis. It is shown t...

Chapter 2 analyzes two key properties of gene regulatory networks, robustness and evolvability, both of which are also quintessential to the evolution of biological systems. After providing a definition of robustness and evolvability, we discuss the relationship between them, and the relationship between the connectivity of gene regulatory networks...

This chapter provides the fundamentals of computational models related to biological evolution and development. It starts with an introduction to evolutionary algorithms for emulating natural evolution in computer systems, including representations, genetic operators, parameter self-adaptation, and their application to single- and multi-objective o...

This chapter investigates the synergies between the evolution and development of the nervous systems and the body plan. It starts with the evolution of an undulatory swimming behavior of an elongated animat when the motor configuration and the neural controller are subject to evolution. Then, it is shown that there is a close coupling between the f...

This chapter evolves both genetic-driven early neural development and activity-dependent neural plasticity. The evolution of primitive neural development focuses on the evolution of a gene regulatory network that can result in a correct gene expression order reflecting the order of cell division, cell migration, and axon growth using the model anim...

This chapter presents various gene-regulated models for self-organizing swarm robots based on a metaphor between multi-cellular morphogenesis and pattern generation of swarm robots. It starts from a simple genetic network model that can generate a predefined pattern to a hierarchical gene regulatory network that can generate patterns that are adapt...

This chapter focuses on evolving the regulatory dynamics most commonly seen in nature. At first, an evolutionary algorithm is adopted to evolve the parameters of a gene regulatory network to generate genetic switches and oscillators. Then, the regulatory logic that combines different regulatory pathways is evolved to synthesize widely seen gene mot...

Based on the evolutionary developmental models presented in the previous chapters, we discuss a possible new approach to artificial general intelligence, which evolves machine learning models that can overcome the limitations of existing deep learning models. It is argued that by taking the evolutionary developmental approach, large models can be e...

The widely employed tiny neural networks (TNNs) in mobile devices are vulnerable to adversarial attacks. However, more advanced research on the robustness of TNNs is highly in demand. This work focuses on improving the robustness of TNNs without sacrificing the model’s accuracy. To find the optimal trade-off networks in terms of the adversarial acc...

Supplementary_Materials_of_SADE_KT

Cognitive diagnosis plays a vital role in modern intelligent education platforms to reveal students' proficiency in knowledge concepts for subsequent adaptive tasks. However, due to the requirement of high model interpretability, existing manually designed cognitive diagnosis models hold too simple architectures to meet the demand of current intell...

The problem of how to assess cross-modality medical image synthesis has been largely unexplored. The most used measures like PSNR and SSIM focus on analyzing the structural features but neglect the crucial lesion location and fundamental k-space speciality of medical images. To overcome this problem, we propose a new metric K-CROSS to spur progress...

In some real-world applications, the optimization problems may involve multiple design stages. At each design stage, the objective is incrementally modified by incorporating more decision variables and optimized. In addition, the fitness evaluations (FEs) are often highly costly. Such optimization problems can be called expensive incremental optimi...

Networked systems widely exist in the modern society, and these systems are always operated in the presence of attacks and errors. The robustness of a network indicates its tolerance against potential damages, which is crucial for the network’s normal functionalities. Damage models including malicious attacks and cascading failures have been consid...

Optimizing building configurations for an efficient use of energy is increasingly receiving attention by current research and several methods have been developed to address this task. Selecting a suitable configuration based on multiple conflicting objectives, such as initial investment cost, recurring cost, robustness with respect to uncertainty o...

Over recent years, there has been a rapid development of deep learning (DL) in both industry and academia fields. However, finding the optimal hyperparameters of a DL model often needs high computational cost and human expertise. To mitigate the above issue, evolutionary computation (EC) as a powerful heuristic search approach has shown significant...

Multi-echelon location-routing problems (ME-LRPs) deal with determining the location of facilities and the routes of vehicles on multi-echelon routing tasks. Since the assignment relationship in multi-echelon routing tasks is uncertain and varying, ME-LRPs are very challenging to solve, especially when the number of the echelons increases. In this...

Popular Transformer networks have been successfully applied to remote sensing (RS) image change detection (CD) identifications and achieve better results than most convolutional neural networks (CNNs), but they still suffer from two main problems. First, the computational complexity of the Transformer grows quadratically with the increase of image...

Surrogate-assisted evolutionary algorithms (SAEAs) have been successfully employed for expensive optimization. However, most SAEAs are designed for expensive unconstrained optimization, and less attention has been paid to expensive optimization with inequality constraints. Therefore, this work proposes a novel SAEA, called surrogate-assisted two-st...

Intelligent manufacturing has promoted the development of Industry 4.0 and enabled the manufacturing industry to gradually move into the stage of intelligence with the rapid development of the Internet of Things and the Industrial Internet. An intelligent manufacturing system is a manufacturing system that can automatically adapt to changing enviro...

Complex optimization problems with hundreds or even thousands of decision variables and dozens of conflicting objectives are not uncommon in the real world. In the past five years, increased research efforts have been dedicated to large-scale multiobjective optimization problems (LSMOPs) by using a variety of search strategies, including variable g...

This article studies the multirobot efficient search (MuRES) for a nonadversarial moving target problem, whose objective is usually defined as either minimizing the target's expected capture time or maximizing the target's capture probability within a given time budget. Different from canonical MuRES algorithms, which target only one specific objec...

Reinforcement learning (RL) is a machine learning approach that trains agents to maximize cumulative rewards through interactions with environments. The integration of RL with deep learning has recently resulted in impressive achievements in a wide range of challenging tasks, including board games, arcade games, and robot control. Despite these suc...

Optimization and learning are two main paradigms of artificial intelligence in addressing complex real-world problems, with their respective focuses but frequently enhanced by each other. Evolutionary multi-objective optimization (EMO) algorithms are a family of nature-inspired algorithms widely used for solving multi-objective optimization problem...

Self-supervised learning (SSL) has become a popular method for generating invariant representations without the need for human annotations. Nonetheless, the desired invariant representation is achieved by utilizing prior online transformation functions on the input data. As a result, each SSL framework is customized for a particular data type, for...

Existing work on offline data-driven optimization mainly focuses on problems in static environments, and little attention has been paid to problems in dynamic environments. Offline data-driven optimization in dynamic environments is a challenging problem because the distribution of collected data varies over time, requiring surrogate models and opt...

Data augmentation is a promising technique for unsupervised anomaly detection in industrial applications, where the availability of positive samples is often limited due to factors such as commercial competition and sample collection difficulties. In this paper, how to effectively select and apply data augmentation methods for unsupervised anomaly...

In many real-world applications of interest, several related optimization tasks can be encountered, where each task is associated with a specific context or personalized information. Moreover, the amount of available data for each task may be highly limited due to the expensive cost involved. Although Bayesian optimization (BO) has emerged as a pro...