Xingyi Zhang

Xingyi Zhang
Anhui University · School of Artifical Intelligence

Prof.

About

166
Publications
79,510
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
5,748
Citations
Additional affiliations
December 2015 - present
Anhui University
Position
  • Professor (Full)
July 2009 - November 2015
Anhui University
Position
  • Professor
June 2006 - June 2009
Huazhong University of Science and Technology
Position
  • PhD Student

Publications

Publications (166)
Article
Full-text available
Pareto front estimation has become an emerging strategy for solving multi-objective optimization problems in recent studies. By approximating the geometrical structure of Pareto front during the evolutionary procedure, some Pareto front estimation approaches have been suggested and shown effectiveness in guiding the search direction of evolutionary...
Article
Full-text available
Evolutionary neural architecture search (ENAS) has recently received increasing attention by effectively finding high-quality neural architectures, which however consumes high computational cost by training the architecture encoded by each individual for complete epochs in individual evaluation. Numerous ENAS approaches have been developed to reduc...
Conference Paper
Full-text available
Evolutionary algorithms and mathematical programming methods are currently the most popular optimizers for solving continuous optimization problems. Owing to the population based search strategies, evolutionary algorithms can find a set of promising solutions without using any problem-specific information. By contrast, with the assistance of gradie...
Article
Full-text available
Large-scale multi-objective optimization problems (LSMOPs) pose challenges to existing optimizers since a set of well-converged and diverse solutions should be found in huge search spaces. While evolutionary algorithms are good at solving small-scale multi-objective optimization problems, they are criticized for the low efficiency in converging to...
Article
Full-text available
The sparse adversarial attack has attracted increasing attention due to the merit of a low attack cost via changing a small number of pixels. However, the generated adversarial examples are easily detected in vision since the perturbation to each pixel is relatively large. To achieve imperceptible and sparse adversarial attacks, this paper formulat...
Article
Full-text available
Many real-world multi-objective optimization problems (MOPs) are characterized by a large number of decision variables, where the decision variables are mostly set to zero in the Pareto optimal solutions. Although some multi-objective evolutionary algorithms (MOEAs) have been tailored for large-scale MOPs in recent years, most of them do not consid...
Article
The JPEG standard is used extensively in image-related applications. The optimization on a JPEG-standard compressor is of high importance for image storage and transmission. In this paper, we propose a versatile and efficient quantization optimization method for image compression. It is based on multi-objective optimization and is JPEG standard-com...
Article
Full-text available
Intensity-modulated radiotherapy (IMRT) is one of the most applied techniques for cancer radiotherapy treatment. The fluence map optimization is an essential part of IMRT plan designing, which has a significant impact on the radiotherapy treatment effect. In fact, the treatment planing of IMRT is an inverse multi-objective optimization problem. Exi...
Article
Full-text available
Intensity-modulated radiotherapy (IMRT) is one of the most popular techniques for cancer treatment. However, existing IMRT planning methods can only generate one solution at a time, and consequently medical physicists should perform the planning process many times to obtain diverse solutions to meet the requirement of a clinical case. Meanwhile, mu...
Article
Full-text available
The Capacitated Vehicle Routing Problem (CVRP) is a widely investigated NP-hard problem, which aims to determine the routes for a fleet of vehicles to serve a group of customers with minimum travel cost. In this paper, a fast evolutionary algorithm is proposed to solve the CVRP. To this end, a relevance matrix storing the probability that two custo...
Article
Full-text available
Evolutionary algorithms (EAs) have become one of the most effective techniques for multi-objective optimization , where a number of variation operators have been developed to handle the problems with various difficulties. While most EAs use a fixed operator all the time, it is a labor-intensive process to determine the best EA for a new problem. He...
Article
Full-text available
Sparse large-scale multi-objective optimization problems (LSMOPs) widely exist in real-world applications, which have the properties of involving a large number of decision variables and sparse Pareto optimal solutions, i.e., most decision variables of these solutions are zero. In recent years, sparse LSMOPs have attracted increasing attentions in...
Article
Full-text available
During the last three decades, evolutionary algorithms (EAs) have shown superiority in solving complex optimization problems, especially those with multiple objectives and non-differentiable landscapes. However, due to the stochastic search strategies, the performance of most EAs deteriorates drastically when handling a large number of decision var...
Article
Unsupervised graph representation learning is a challenging task that embeds graph data into a low-dimensional space without label guidance. Recently, graph autoencoders have been proven to be an effective way to solve this problem in some attributed networks. However, most existing graph autoencoder-based embedding algorithms only reconstruct the...
Preprint
Full-text available
Evolutionary neural architecture search (ENAS) has recently received increasing attention by effectively finding high-quality neural architectures, which however consumes high computational cost by training the architecture encoded by each individual for complete epochs in individual evaluation. Numerous ENAS approaches have been developed to reduc...
Article
Feature selection (FS) is an NP-hard combinatorial optimization problem, which aims to select the most relevant features from a large number of candidates. Recently, the FS in classification has been handled as a bi-objective optimization problem, where both the classification error and the number of selected features are minimized simultaneously....
Article
Full-text available
With the development of neural architecture search, the performance of deep neural networks has been considerably enhanced with less human expertise. While existing work mainly focuses on the development of optimizers, the design of encoding scheme is still in its infancy. This paper thus proposes a novel encoding scheme for neural architecture sea...
Article
Full-text available
Community detection in large-scale complex networks has recently received significant attention as the volume of available data is becoming larger. The use of evolutionary algorithms (EAs) for community detection in large-scale networks has gained considerable popularity because these algorithms are fairly effective in networks with a relatively sm...
Article
Full-text available
Large-scale dynamic vehicle routing problem (LSDVRP) is exhibiting extensive application prospect with the rapid growth of online logistics, whereas a few approaches have been developed to address LSDVRPs. The difficulty in solving LSDVRPs lies in that it requires quick response and high adaptability to numerous newly appeared customers in LSDVRPs....
Article
Full-text available
Multi-objective evolutionary algorithms (MOEAs) have shown promising performance in solving various optimization problems, but their performance may deteriorate drastically when tackling problems containing a large number of decision variables. In recent years, a large amount of efforts have been devoted to addressing the challenges brought by larg...
Article
The task of community detection in attributed networks is to find a good community partition in terms of both topology structure and node attribute. Despite that a number of algorithms have been suggested for community detection in attributed networks, most of them suffer from considerable performance deterioration when the community structure is n...
Preprint
Full-text available
In the past three decades, a large number of metaheuristics have been proposed and shown high performance in solving complex optimization problems. While most variation operators in existing metaheuristics are empirically designed, this paper aims to design new operators automatically, which are expected to be search space independent and thus exhi...
Article
Full-text available
Recently, multi-objective evolutionary algorithms (MOEAs) have been shown promising performance for detecting overlapping community structure in complex networks. However, it is still challenging to design MOEAs for overlapping community detection on large-scale complex networks due to the curse of dimensionality. Along this avenue, this paper prop...
Article
Full-text available
Due to natural disasters or system failures, the facility has the risk of disruption, and thus improving the location reliability under uncertainty of facilities becomes an important issue. In this paper, we propose a multi-objective facility location problem under uncertainty of facilities, where two objectives on reliability are constructed and m...
Article
Many link prediction algorithms regarding single-layer social networks have been proposed, and however, how to predict interlayer links in multiplex social networks is still in the initial stage. In fact, the prediction of interlayer links in multiplex networks is of great significance, which is closely related to network security, product recommen...
Conference Paper
Full-text available
The performance of most multi-objective evolutionary algorithms (MOEAs) usually degenerates when they are adopted to tackle large-scale multi-objective optimization problems (LSMOPs) involving a large number of decision variables. While LSMOPs attract increasing attention in the evolutionary computation community in recent years, a number of delica...
Article
Given a fixed total budget and a predefined cost model, the budgeted influence maximization problem aims to find a subset of nodes to maximize the influence spread in social networks while its cost should be no more than the fixed total budget. In this paper, we propose a local-global influence indicator based constrained evolutionary algorithm, na...
Chapter
The performance of most multi-objective evolutionary algorithms (MOEAs) usually degenerates when they are adopted to tackle large-scale multi-objective optimization problems (LSMOPs) involving a large number of decision variables. While LSMOPs attract increasing attention in the evolutionary computation community in recent years, a number of delica...
Article
Full-text available
It has been widely recognized that the efficient training of neural networks (NNs) is crucial to the classification performance. While a series of gradient based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyper-parameters. Owing to the high robustness and wide applic...
Article
Medical image classification is an important task in computer aided diagnosis (CAD) systems. Its performance is critically determined by the descriptiveness and discriminative power of features extracted from images. With rapid development of deep learning, deep convolutional neural networks (CNNs) have been widely used to learn the optimal high-le...
Article
Full-text available
Dynamic vehicle routing problems (DVRPs) have become a hot research topic due to their significance in logistics, although it is still very challenging for existing algorithms to solve DVRPs due to the dynamically changing customer requests during the optimization. In this paper, we propose a pairwise proximity learning-based ant colony algorithm,...
Article
Full-text available
The algorithm recommendation is attracting increasing attention in solving real-world capacitated vehicle routing problems (CVRPs), due to the fact that existing meta-heuristic algorithms often show different performances on different CVRPs. To effectively perform algorithm recommendation for CVRPs, it becomes vital to extract suitable features to...
Article
Full-text available
Constrained multi-objective optimization problems (CMOPs) are difficult to handle because objectives and constraints need to be considered simultaneously , especially when the constraints are extremely complex. Some recent algorithms work well when dealing with CMOPs with a simple feasible region ; however, the effectiveness of most algorithms degr...
Article
Full-text available
Constrained multiobjective optimization problems (CMOPs) widely exist in real-world applications, and they are challenging for conventional evolutionary algorithms (EAs) due to the existence of multiple constraints and objectives. When the number of objectives or decision variables is scaled up in CMOPs, the performance of EAs may degenerate dramat...
Article
Full-text available
Multi-modal multi-objective optimization problems (MMOPs) widely exist in real-world applications, which have multiple equivalent Pareto optimal solutions that are similar in the objective space but totally different in the decision space. While some evolutionary algorithms (EAs) have been developed to find the equivalent Pareto optimal solutions i...
Article
Positive and unlabeled (PU) learning has attracted increasing interests in recent years. Despite that a number of PU learning algorithms have been proposed, most of them are subject to some assumptions about unlabeled sample distribution and objective functions, which makes them difficult to be adopted for real applications. To this end, in this pa...
Article
Full-text available
In real-world applications, there exist a lot of multi-objective optimization problems whose Pareto optimal solutions are sparse, i.e., most variables of these solutions are zero. Generally, many sparse multi-objective optimization problems (SMOPs) contain a large number of variables, which pose grand challenges for evolutionary algorithms to find...
Article
Full-text available
As the size of available networks is continuously increasing (even with millions of nodes), large-scale complex networks are receiving significant attention. While existing overlapping-community detection algorithms are quite effective in analyzing complex networks, most of these algorithms suffer from scalability issues when applied to large-scale...
Article
Full-text available
Identifying functional modules in protein-protein interaction (PPI) networks elucidates cellular organization and mechanism. Various methods have been proposed to identify the functional modules in PPI networks, but most of these methods do not consider the noisy links in PPI networks. They achieve a competitive performance on the PPI networks with...
Article
Full-text available
As revealed by the no free lunch theorem, no single algorithm can outperform any others on all classes of optimization problems. To tackle this issue, methods for recommending an existing algorithm for solving given problems have been proposed. However, existing recommendation methods for continuous optimization suffer from low practicability and t...
Article
Full-text available
Both objective optimization and constraint satisfaction are crucial for solving constrained multi-objective optimization problems, but existing evolutionary algorithms encounter difficulties in striking a good balance between them when tackling complex feasible regions. To address this issue, this paper proposes a two-stage evolutionary algorithm,...
Conference Paper
Full-text available
It has been widely recognized that evolutionary computation is one of the most effective techniques for solving complex optimization problems. As a group of meta-heuristics inspired by nature, the superiority of evolutionary algorithms is mainly attributed to the evolution of multiple candidate solutions, which can strike a balance between explorat...
Article
Full-text available
Constrained multi-objective optimization problems (CMOPs) are challenging because of the difficulty in handling both multiple objectives and constraints. While some evolutionary algorithms have demonstrated high performance on most CMOPs, they exhibit bad convergence or diversity performance on CMOPs with small feasible regions. To remedy this issu...
Article
Dynamic vehicle routing problem (DVRP) has attracted increasing attention due to its wide applications in logistics. Compared with the static vehicle routing problem, DVRP is characterized by the prior unknown customer requests dynamically appearing in route execution. Nevertheless, the newly appeared customers pose a great challenge to route optim...
Chapter
The identification of disease modules has attracted increasing attention due to the importance in comprehending pathogenesis of complex diseases. Most of the existing methods were based on the protein-protein interaction (PPI) networks with the incompleteness and incorrectness of the interactome, which results in many disease-related proteins and p...
Article
Full-text available
After decades of research, it has been widely recognized that complex diseases are caused by the dysfunction of biological systems induced by disease-associated genes. To understand the molecular basis of complex diseases, many efforts have been devoted to the identification of disease-related gene modules in the last two decades, by means of explo...
Article
Full-text available
Due to the curse of dimensionality of search space, it is extremely difficult for evolutionary algorithms to approximate the optimal solutions of large-scale multi-objective optimization problems (LMOPs) by using a limited budget of evaluations. If the Pareto optimal subspace is approximated during the evolutionary process, the search space can be...
Article
The critical node detection based on cascade model is a very important way for analyzing network vulnerability and has recently attracted the attention of many researchers in complex network area. Most of existing works aim to design effective attack strategies which lead to maximal damage to the network (i.e. the destructiveness of the attack), wh...
Article
Full-text available
Community detection in complex networks has aroused wide attention, since it can find some useful information hidden in the networks. Many different community detection algorithms have been proposed to detect the communities in a variety of networks. However, as the ratio of each node connecting with the nodes in other communities increases, namely...
Conference Paper
Full-text available
In the last two decades, many evolutionary algorithms have shown promising performance in solving a variety of multi-objective optimization problems (MOPs). Since there does not exist an evolutionary algorithm having the best performance on all the MOPs, it is unreasonable to use a single evolutionary algorithm to tackle all the MOPs. Since many re...