Xiaoyu He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaoyu He has a total of 42 co-authors. Here are the top co-authors by number of shared publications:
- Yuren Zhou
School of Software Engineering, Sun Yat-sen University, Zhuhai, China
14 shared publications - Qianlong Dang
Northwest A & F University
8 shared publications - Zefeng Chen
Sun Yat-sen University
8 shared publications - Zibin Zheng
Sun Yat-Sen University, Guangzhou, China
7 shared publications - Maoguo Gong
Xidian University, Xi'an, China
3 shared publications - Tao Zhan
Northwest A&F University
3 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computational Intelligence Magazine
- Vol. 21 (4) , 52-66
A Fuzzy Diversity Handling Technique-Based Multimodal Multi-Objective Evolutionary Algorithm and Its Base Station Location Applications [Research Frontier]
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computational Intelligence Magazine
- Vol. 21 (4) , 52-66
A Fuzzy Diversity Handling Technique-Based Multimodal Multi-Objective Evolutionary Algorithm and Its Base Station Location Applications [Research Frontier]
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 2396-2408
Panorama: Unveiling Latent Dependencies for Microservice Autoscaling via Meta-learning
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 2396-2408
Open AccessPanorama: Unveiling Latent Dependencies for Microservice Autoscaling via Meta-learning
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (5) , 3436-3450
Adaptive Convergence Indicator and Neighborhood Fuzzy Crowding Distance for Multimodal Multi-Objective Optimization
Multimodal multi-objective optimization is a popular research direction characterized by different points on different Pareto optimal solution sets (PSs) in the decision space, corresponding to the same point on the Pareto front in the objective space. In addition, there may exist some multimodal multi-objective optimization problems (MMOPs) with local PSs. Finding all the equivalent global PSs and local PSs is the key to solving MMOPs. To solve these problems, this paper proposes a multimodal multi-objective evolutionary algorithm (MMOEA) based on the adaptive convergence indicator and neighborhood fuzzy crowding distance (ACEA-NFCD). The adaptive convergence indicator is able to calculate the local convergence indicator and global convergence indicator through the adaptive selection of neighborhood knowledge, which can effectively preserve all global PSs and local PSs and exclude the interference of isolated solutions. Moreover, in order to increase the diversity of the population, neighborhood crowding distances in the decision space and the objective space are integrated via fuzzy set theory, improving the truncation and selection process. The superior performance of ACEA-NFCD is demonstrated by experimentally comparing it with nine of the most advanced MMOEAs on four benchmark suites and one practical application of map-based distance minimization.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (5) , 3436-3450
Adaptive Convergence Indicator and Neighborhood Fuzzy Crowding Distance for Multimodal Multi-Objective Optimization
Multimodal multi-objective optimization is a popular research direction characterized by different points on different Pareto optimal solution sets (PSs) in the decision space, corresponding to the same point on the Pareto front in the objective space. In addition, there may exist some multimodal multi-objective optimization problems (MMOPs) with local PSs. Finding all the equivalent global PSs and local PSs is the key to solving MMOPs. To solve these problems, this paper proposes a multimodal multi-objective evolutionary algorithm (MMOEA) based on the adaptive convergence indicator and neighborhood fuzzy crowding distance (ACEA-NFCD). The adaptive convergence indicator is able to calculate the local convergence indicator and global convergence indicator through the adaptive selection of neighborhood knowledge, which can effectively preserve all global PSs and local PSs and exclude the interference of isolated solutions. Moreover, in order to increase the diversity of the population, neighborhood crowding distances in the decision space and the objective space are integrated via fuzzy set theory, improving the truncation and selection process. The superior performance of ACEA-NFCD is demonstrated by experimentally comparing it with nine of the most advanced MMOEAs on four benchmark suites and one practical application of map-based distance minimization.
- 13 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (8) , 1-15
Momentum-Based Zeroth-Order Gradient Method for Distributed Black-box Optimization
We consider a class of distributed black-box optimization problems where client-side objective functions are accessible only through queries. This setting faces a dual challenge: the convergence of distributed zeroth-order methods is severely hindered by data heterogeneity and the high variance inherent in gradient estimates. To address this, we propose a distributed zeroth-order stochastic normalized gradient descent with momentum (DZO-SNGM) algorithm. Our method features multiple local zeroth-order updates on each client, followed by a global model aggregation and a single, stabilizing momentum update on the server. We establish theoretical convergence guarantees for DZO-SNGM on non-convex objectives. Extensive experiments on image classification and distributed black-box adversarial attacks demonstrate that DZO-SNGM not only converges significantly faster but also achieves superior final performance than state-of-the-art methods. The code is available at https://github.com/dqlme/DZO-SNGM.git.
- 13 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (8) , 1-15
Momentum-Based Zeroth-Order Gradient Method for Distributed Black-box Optimization
We consider a class of distributed black-box optimization problems where client-side objective functions are accessible only through queries. This setting faces a dual challenge: the convergence of distributed zeroth-order methods is severely hindered by data heterogeneity and the high variance inherent in gradient estimates. To address this, we propose a distributed zeroth-order stochastic normalized gradient descent with momentum (DZO-SNGM) algorithm. Our method features multiple local zeroth-order updates on each client, followed by a global model aggregation and a single, stabilizing momentum update on the server. We establish theoretical convergence guarantees for DZO-SNGM on non-convex objectives. Extensive experiments on image classification and distributed black-box adversarial attacks demonstrate that DZO-SNGM not only converges significantly faster but also achieves superior final performance than state-of-the-art methods. The code is available at https://github.com/dqlme/DZO-SNGM.git.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-16
LADA: Latent-Space Adversarial Diffusion Attack in Remote Sensing
Deep neural networks (DNNs) have achieved remarkable progress in remote sensing image (RSI) analysis, yet their vulnerability to subtle adversarial perturbations poses a critical threat to safety-critical applications such as environmental monitoring. While black-box attacks have garnered attention for their practicality, existing methods face a dilemma in RSI scenarios: restricted attacks often result in compromised image quality and limited stealthiness, whereas unrestricted attacks risk degrading transferability. To address this challenge, this paper proposes the latent-space adversarial diffusion attack framework (LADA), which focuses on balancing stealthiness and transferability in adversarial attacks against RSI models. LADA employs a pre-trained diffusion model to map high-resolution RSIs into a low-dimensional latent space, enabling semantic-level perturbation optimization while avoiding pixel-wise explicit noise. Additionally, text prompts are automatically generated using a large multimodal model to guide adversarial sample synthesis, ensuring semantic consistency. To enhance perturbation search efficiency in the latent space, a hybrid strategy combining multi-scale sampling and covariance matrix adaptation evolution strategy is introduced. Extensive experiments demonstrate that LADA achieves superior performance across multiple RSI datasets, model architectures, and defense mechanisms. This paper establishes a benchmark for high-stealthiness and high-transferability adversarial attacks, advancing the secure deployment of DNNs in remote sensing applications.
- 10 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-16
LADA: Latent-Space Adversarial Diffusion Attack in Remote Sensing
Deep neural networks (DNNs) have achieved remarkable progress in remote sensing image (RSI) analysis, yet their vulnerability to subtle adversarial perturbations poses a critical threat to safety-critical applications such as environmental monitoring. While black-box attacks have garnered attention for their practicality, existing methods face a dilemma in RSI scenarios: restricted attacks often result in compromised image quality and limited stealthiness, whereas unrestricted attacks risk degrading transferability. To address this challenge, this paper proposes the latent-space adversarial diffusion attack framework (LADA), which focuses on balancing stealthiness and transferability in adversarial attacks against RSI models. LADA employs a pre-trained diffusion model to map high-resolution RSIs into a low-dimensional latent space, enabling semantic-level perturbation optimization while avoiding pixel-wise explicit noise. Additionally, text prompts are automatically generated using a large multimodal model to guide adversarial sample synthesis, ensuring semantic consistency. To enhance perturbation search efficiency in the latent space, a hybrid strategy combining multi-scale sampling and covariance matrix adaptation evolution strategy is introduced. Extensive experiments demonstrate that LADA achieves superior performance across multiple RSI datasets, model architectures, and defense mechanisms. This paper establishes a benchmark for high-stealthiness and high-transferability adversarial attacks, advancing the secure deployment of DNNs in remote sensing applications.
- 11 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 30 (1) , 186-198
Data-Driven Evolutionary Algorithm Based on Inductive Graph Neural Networks for Multimodal Multiobjective Optimization
In multimodal multi-objective optimization problems (MMOPs), multiple solutions on different Pareto optimal solution sets (PSs) are mapped to the same point on the Pareto front. Considering these different solutions can provide users with richer decisions, the search of multiple PSs is crucial when solving MMOPs. To this end, many multimodal multi-objective evolutionary algorithms (MMOEAs) often employ intricate mechanisms to maintain the diversity of the offspring in mating selection, but ignore to learn PSs. In this paper, a data-driven evolutionary algorithm based on inductive graph neural networks (DEA-IGNN) is proposed to solve MMOPs, which successfully learns the PSs topology by the graph structure to generate offspring with good performance. Specifically, a graph topology construction method based on Euclidean distance in the decision space is designed. It determines the neighborhood by calculating the Euclidean distance of individuals in the decision space and establishes the topological relationships to construct the graphs representing of population distribution. On this basis, a model based on inductive graph neural networks is constructed to assist offspring reproduction, which can learn unknown nodes by sampling and aggregating existing information. Moreover, a data-driven reproduction strategy is proposed to predict offspring with the good diversity and convergence, which uses the traditional variation operators to generate training data and adopts these data to train the model. The proposed DEA-IGNN is implemented and compared with eleven competitive MMOEAs on three test suites and a practical problem. The experimental results show that DEA-IGNN has good performance.
- 11 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 30 (1) , 186-198
Data-Driven Evolutionary Algorithm Based on Inductive Graph Neural Networks for Multimodal Multiobjective Optimization
In multimodal multi-objective optimization problems (MMOPs), multiple solutions on different Pareto optimal solution sets (PSs) are mapped to the same point on the Pareto front. Considering these different solutions can provide users with richer decisions, the search of multiple PSs is crucial when solving MMOPs. To this end, many multimodal multi-objective evolutionary algorithms (MMOEAs) often employ intricate mechanisms to maintain the diversity of the offspring in mating selection, but ignore to learn PSs. In this paper, a data-driven evolutionary algorithm based on inductive graph neural networks (DEA-IGNN) is proposed to solve MMOPs, which successfully learns the PSs topology by the graph structure to generate offspring with good performance. Specifically, a graph topology construction method based on Euclidean distance in the decision space is designed. It determines the neighborhood by calculating the Euclidean distance of individuals in the decision space and establishes the topological relationships to construct the graphs representing of population distribution. On this basis, a model based on inductive graph neural networks is constructed to assist offspring reproduction, which can learn unknown nodes by sampling and aggregating existing information. Moreover, a data-driven reproduction strategy is proposed to predict offspring with the good diversity and convergence, which uses the traditional variation operators to generate training data and adopts these data to train the model. The proposed DEA-IGNN is implemented and compared with eleven competitive MMOEAs on three test suites and a practical problem. The experimental results show that DEA-IGNN has good performance.
- 28 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-14
Boosting Adversarial Transferability by Batchwise Amplitude Spectrum Normalization
We consider the black-box adversarial attack problem in the field of remote sensing images (RSIs) to reveal the vulnerabilities of various deep neural networks (DNN), including classification and semantic segmentation models. Existing adversarial attack methods typically focus solely on maximizing attack success rates under given perturbation constraints, neglecting the differences between adversarial samples and clean images. We propose a batch-wise amplitude spectrum normalization method (BAMPN), which is a plug-and-play and transfer-based blackbox attack strategy. By utilizing the Fourier transform, we convert RSIs from the spatial domain to the frequency domain to obtain the amplitude spectrum, which is normalized within the batch. Moreover, we employ a moving average strategy to retain the historical amplitudes of the batch, enhancing input diversity. By mixing the low-level statistical features of RSIs, BAMPN reduces the differences between adversarial samples and clean images while improving attack transferability. In addition, BAMPN is applicable not only to RSIs classification tasks but also directly to semantic segmentation tasks, as it preserves the spatial semantic structure of RSIs. We conduct extensive experiments using 20 DNN models and 4 benchmark RSIs datasets, comparing our method against 14 state-of-the-art approaches. The results demonstrate that BAMPN achieves superior attack performance while ensuring a promising similarity between adversarial and clean samples.
- 28 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-14
Boosting Adversarial Transferability by Batchwise Amplitude Spectrum Normalization
We consider the black-box adversarial attack problem in the field of remote sensing images (RSIs) to reveal the vulnerabilities of various deep neural networks (DNN), including classification and semantic segmentation models. Existing adversarial attack methods typically focus solely on maximizing attack success rates under given perturbation constraints, neglecting the differences between adversarial samples and clean images. We propose a batch-wise amplitude spectrum normalization method (BAMPN), which is a plug-and-play and transfer-based blackbox attack strategy. By utilizing the Fourier transform, we convert RSIs from the spatial domain to the frequency domain to obtain the amplitude spectrum, which is normalized within the batch. Moreover, we employ a moving average strategy to retain the historical amplitudes of the batch, enhancing input diversity. By mixing the low-level statistical features of RSIs, BAMPN reduces the differences between adversarial samples and clean images while improving attack transferability. In addition, BAMPN is applicable not only to RSIs classification tasks but also directly to semantic segmentation tasks, as it preserves the spatial semantic structure of RSIs. We conduct extensive experiments using 20 DNN models and 4 benchmark RSIs datasets, comparing our method against 14 state-of-the-art approaches. The results demonstrate that BAMPN achieves superior attack performance while ensuring a promising similarity between adversarial and clean samples.
- Top Cited Papers
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computational Intelligence Magazine
- Vol. 20 (1) , 34-49
Transformer-Based Intelligent Prediction Model for Multimodal Multi-Objective Optimization
Traditional multimodal multi-objective evolutionary algorithms (MMOEAs) usually adopt the reproduction strategy based on meta-heuristic and fail to make full use of changes of multi-generation population distribution, which can help the population to further evolve and improve the exploitation ability of algorithms. To address this issue, this paper proposes a deep learning-based evolutionary algorithm (DLEA), which converts historical population information into time series and uses deep neural networks to predict the population distribution. Specifically, a transformer-based prediction model is constructed to reproduce promising offspring by capturing changes of population distribution in adjacent generations. Moreover, many MMOEAs focus only on global Pareto optimal solution sets (PSs) and ignore local PSs. Although local PSs are inferior to global PSs in terms of objective values, the cost of obtaining global PSs in some practical applications is huge. Local PSs with similar objectives to global PSs are acceptable alternatives for decision makers. Therefore, a difference-based attention mechanism is designed for archive update, which saves solutions on the global PSs and local PSs by calculating the attention value. Experimental studies indicate that DLEA outperforms other six competitive MMOEAs.
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computational Intelligence Magazine
- Vol. 20 (1) , 34-49
Top Cited PapersTransformer-Based Intelligent Prediction Model for Multimodal Multi-Objective Optimization
Traditional multimodal multi-objective evolutionary algorithms (MMOEAs) usually adopt the reproduction strategy based on meta-heuristic and fail to make full use of changes of multi-generation population distribution, which can help the population to further evolve and improve the exploitation ability of algorithms. To address this issue, this paper proposes a deep learning-based evolutionary algorithm (DLEA), which converts historical population information into time series and uses deep neural networks to predict the population distribution. Specifically, a transformer-based prediction model is constructed to reproduce promising offspring by capturing changes of population distribution in adjacent generations. Moreover, many MMOEAs focus only on global Pareto optimal solution sets (PSs) and ignore local PSs. Although local PSs are inferior to global PSs in terms of objective values, the cost of obtaining global PSs in some practical applications is huge. Local PSs with similar objectives to global PSs are acceptable alternatives for decision makers. Therefore, a difference-based attention mechanism is designed for archive update, which saves solutions on the global PSs and local PSs by calculating the attention value. Experimental studies indicate that DLEA outperforms other six competitive MMOEAs.
- 1 February 2024
- Published by Elsevier in Artificial Intelligence
- Vol. 329
A stochastic process approach for multi-agent path finding with non-asymptotic performance guarantees
- 1 February 2024
- Published by Elsevier in Artificial Intelligence
- Vol. 329
A stochastic process approach for multi-agent path finding with non-asymptotic performance guarantees