Jianyong Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jianyong Sun has a total of 96 co-authors. Here are the top co-authors by number of shared publications:
- Qingfu Zhang
City University of Hong Kong, Hong Kong, China
18 shared publications - Zongben Xu
School of Mathematics and Statistics, Xian Jiaotong University, Xian, China
14 shared publications - Jialong Shi
Xi'an Jiaotong University, Xi'an, China
11 shared publications - Haotian Zhang
Frontier Institute of Science and Technology, Xian Jiaotong University, Xian, China
10 shared publications Zongben Xu
School of Mathematics and Statistics, Xian Jiaotong University, Xian, China
9 shared publicationsQingfu Zhang
8 shared publications
Latest Publications
- Open Access
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1335-1343
Vibroseis Vehicle Routing Problem with Spatio-Temporal Coupled Constraints
- 13 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1335-1343
Open AccessVibroseis Vehicle Routing Problem with Spatio-Temporal Coupled Constraints
- 20 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 9094-9107
A Block-Based Babai Detector for Detecting the Integer Parameter Vector in a Box-Constrained Linear Model
Detecting the integer parameter vector in a box-constrained linear model with additive Gaussian noise arises from many applications. The maximum likelihood (ML) detector detects the integer parameter vector by solving a Box-constrained Integer Least Squares (BILS) problem and achieves the highest success probability (i.e., the probability that the detected integer vector equals the original integer vector). However, due to the high complexity of the ML detector, the Babai detector is frequently used to approximate solutions to the BILS problem, especially in time-constrained applications. Considering the success probability achieved by existing Babai detector frameworks is not always satisfying, this paper focuses on proposing a fast block-based Babai detector framework within polynomial complexity to narrow the gap to the ML detector. Unlike element-wise Babai detectors, the proposed method partitions the model matrix into blocks and applies the appropriately sized ML detector to each block. Theoretical analysis shows that the success probability of the block-based Babai detector increases with the block size and therefore is better than the Babai detector. To further improve the success probability, an extended block-based Babai detector is proposed with a reasonable increase in complexity. Simulation results illustrate the theoretical findings and indicate that the proposed detectors achieve a better trade-off between the success probability and complexity compared with conventional Zero-Forcing (ZF), Successive Interference Cancellation (SIC)/Babai detectors, as well as the generalized Babai detector proposed by Chang et al.. For example, in a 16 × 16 MIMO system with 16-QAM modulation, the (extedned) block-based Babai detector can improve the success probability by 5.3% (8.7%) at SNR = 15dB and achieve a gain of approximately 1.5 dB (2 dB) at a BER of 10−3, compared with Chang et al.’s generalized Babai detector, while requiring only 45.1% (57.9%) of the computational complexity on average over the tested SNR range.
- 20 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 9094-9107
A Block-Based Babai Detector for Detecting the Integer Parameter Vector in a Box-Constrained Linear Model
Detecting the integer parameter vector in a box-constrained linear model with additive Gaussian noise arises from many applications. The maximum likelihood (ML) detector detects the integer parameter vector by solving a Box-constrained Integer Least Squares (BILS) problem and achieves the highest success probability (i.e., the probability that the detected integer vector equals the original integer vector). However, due to the high complexity of the ML detector, the Babai detector is frequently used to approximate solutions to the BILS problem, especially in time-constrained applications. Considering the success probability achieved by existing Babai detector frameworks is not always satisfying, this paper focuses on proposing a fast block-based Babai detector framework within polynomial complexity to narrow the gap to the ML detector. Unlike element-wise Babai detectors, the proposed method partitions the model matrix into blocks and applies the appropriately sized ML detector to each block. Theoretical analysis shows that the success probability of the block-based Babai detector increases with the block size and therefore is better than the Babai detector. To further improve the success probability, an extended block-based Babai detector is proposed with a reasonable increase in complexity. Simulation results illustrate the theoretical findings and indicate that the proposed detectors achieve a better trade-off between the success probability and complexity compared with conventional Zero-Forcing (ZF), Successive Interference Cancellation (SIC)/Babai detectors, as well as the generalized Babai detector proposed by Chang et al.. For example, in a 16 × 16 MIMO system with 16-QAM modulation, the (extedned) block-based Babai detector can improve the success probability by 5.3% (8.7%) at SNR = 15dB and achieve a gain of approximately 1.5 dB (2 dB) at a BER of 10−3, compared with Chang et al.’s generalized Babai detector, while requiring only 45.1% (57.9%) of the computational complexity on average over the tested SNR range.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (4) , 3495-3506
Multi-Channel Fusion Deep Wavelet Spectrum Network for Epileptic Signal Classification
Recent developments in the detection of epilepsy and classification of seizures using electroencephalogram (EEG) signals have shown notable progress, yet they still face some challenges. For example, tensor decomposition techniques struggle with high computational demands, and deep learning methods often do not fully utilize the spatial structure of EEG data. This paper presents MavenNet, a Multichannel Wavelet Convolutional Network aimed at improving automated detection of epilepsy and seizure classification. MavenNet begins by applying the continuous wavelet transform to represent the multichannel temporal spectrum as a third-order tensor, which is then processed through multichannel convolution operations. To enhance the interpretability of the model, Class Activation Mapping (CAM) is used to visualize the spectrogram features that are essential for making classification decisions. Experimental results from three widely used datasets and one private dataset indicate that MavenNet outperforms leading algorithms. The proposed model maintains the spatial structure of EEG signals and increases the transparency and reliability of classification outcomes, positioning it as a valuable tool for clinical diagnosis of epilepsy.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (4) , 3495-3506
Multi-Channel Fusion Deep Wavelet Spectrum Network for Epileptic Signal Classification
Recent developments in the detection of epilepsy and classification of seizures using electroencephalogram (EEG) signals have shown notable progress, yet they still face some challenges. For example, tensor decomposition techniques struggle with high computational demands, and deep learning methods often do not fully utilize the spatial structure of EEG data. This paper presents MavenNet, a Multichannel Wavelet Convolutional Network aimed at improving automated detection of epilepsy and seizure classification. MavenNet begins by applying the continuous wavelet transform to represent the multichannel temporal spectrum as a third-order tensor, which is then processed through multichannel convolution operations. To enhance the interpretability of the model, Class Activation Mapping (CAM) is used to visualize the spectrogram features that are essential for making classification decisions. Experimental results from three widely used datasets and one private dataset indicate that MavenNet outperforms leading algorithms. The proposed model maintains the spatial structure of EEG signals and increases the transparency and reliability of classification outcomes, positioning it as a valuable tool for clinical diagnosis of epilepsy.
- Open Access
MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Research
Operations Research (OR) relies on expert-driven modeling-a slow and fragile process ill-suited to novel scenarios. While large language models (LLMs) can automatically translate natural language into optimization models, existing approaches either rely on costly post-training or employ multi-agent frameworks, yet most still lack reliable collaborative error correction and task-specific retrieval, often leading to incorrect outputs. We propose MIRROR, a fine-tuning-free, end-to-end multi-agent framework that directly translates natural language optimization problems into mathematical models and solver code. MIRROR integrates two core mechanisms: (1) execution-driven iterative adaptive revision for automatic error correction, and (2) hierarchical retrieval to fetch relevant modeling and coding exemplars from a carefully curated exemplar library. Experiments show that MIRROR outperforms existing methods on standard OR benchmarks, with notable results on complex industrial datasets such as IndustryOR and Mamo-ComplexLP. By combining precise external knowledge infusion with systematic error correction, MIRROR provides non-expert users with an efficient and reliable OR modeling solution, overcoming the fundamental limitations of general-purpose LLMs in expert optimization tasks.
Open AccessMIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Research
Operations Research (OR) relies on expert-driven modeling-a slow and fragile process ill-suited to novel scenarios. While large language models (LLMs) can automatically translate natural language into optimization models, existing approaches either rely on costly post-training or employ multi-agent frameworks, yet most still lack reliable collaborative error correction and task-specific retrieval, often leading to incorrect outputs. We propose MIRROR, a fine-tuning-free, end-to-end multi-agent framework that directly translates natural language optimization problems into mathematical models and solver code. MIRROR integrates two core mechanisms: (1) execution-driven iterative adaptive revision for automatic error correction, and (2) hierarchical retrieval to fetch relevant modeling and coding exemplars from a carefully curated exemplar library. Experiments show that MIRROR outperforms existing methods on standard OR benchmarks, with notable results on complex industrial datasets such as IndustryOR and Mamo-ComplexLP. By combining precise external knowledge infusion with systematic error correction, MIRROR provides non-expert users with an efficient and reliable OR modeling solution, overcoming the fundamental limitations of general-purpose LLMs in expert optimization tasks.
- Open Access
Quality-Diversity Optimization as Multi-Objective Optimization
The Quality-Diversity (QD) optimization aims to discover a collection of high-performing solutions that simultaneously exhibit diverse behaviors within a user-defined behavior space. This paradigm has stimulated significant research interest and demonstrated practical utility in domains including robot control, creative design, and adversarial sample generation. A variety of QD algorithms with distinct design principles have been proposed in recent years. Instead of proposing a new QD algorithm, this work introduces a novel reformulation by casting the QD optimization as a multi-objective optimization (MOO) problem with a huge number of optimization objectives. By establishing this connection, we enable the direct adoption of well-established MOO methods, particularly set-based scalarization techniques, to solve QD problems through a collaborative search process. We further provide a theoretical analysis demonstrating that our approach inherits theoretical guarantees from MOO while providing desirable properties for the QD optimization. Experimental studies across several QD applications confirm that our method achieves performance competitive with state-of-the-art QD algorithms.
Open AccessQuality-Diversity Optimization as Multi-Objective Optimization
The Quality-Diversity (QD) optimization aims to discover a collection of high-performing solutions that simultaneously exhibit diverse behaviors within a user-defined behavior space. This paradigm has stimulated significant research interest and demonstrated practical utility in domains including robot control, creative design, and adversarial sample generation. A variety of QD algorithms with distinct design principles have been proposed in recent years. Instead of proposing a new QD algorithm, this work introduces a novel reformulation by casting the QD optimization as a multi-objective optimization (MOO) problem with a huge number of optimization objectives. By establishing this connection, we enable the direct adoption of well-established MOO methods, particularly set-based scalarization techniques, to solve QD problems through a collaborative search process. We further provide a theoretical analysis demonstrating that our approach inherits theoretical guarantees from MOO while providing desirable properties for the QD optimization. Experimental studies across several QD applications confirm that our method achieves performance competitive with state-of-the-art QD algorithms.
- 17 September 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Imaging Sciences
- Vol. 18 (3) , 1929-1962
Multimodal Disentanglement by Latent Variable Separation with Surrogate Modal Specifics and Mixture-of-Distributions Priors
The multimodal variational autoencoder (VAE) is a probabilistic latent variable model for modeling the generative process of multiple modalities. Existing multimodal VAEs typically divide the latent variable into two types of variables, aiming to represent shared information across modalities and specific information for each modality. However, previous models lack a mechanism to ensure the disentanglement of these two latent variables, causing degraded generation coherence and quality. Failing in disentanglement hampers their performances, particularly concerning the unconditional coherence metric. Further, since these models are derived from VAE, they inherently struggle to generate high-quality samples. In this work, a new probabilistic latent variable model, named multimodal VAE with mixture-of-distributions prior (MVP), is proposed to address these issues. A mixture of conditional distributions is used as priors for the two latent variables separately, while each mixture component is conditioned on learnable pseudoinputs. These pseudoinputs function as prototypes for modal-specific information, which are parameters of the prior for modal-specific latent variables. Experiments conducted on the PolyMNIST and Tri-modal Fashion-MNIST datasets show that MVP outperforms all previous models in terms of generation coherence and quality. Furthermore, experiments confirm that MVP achieves better disentanglement between the two latent variables than that of other existing methods. An implementation of the MVP model is available at https://github.com/fan222/MVP_multimodal-vae-with-mixture-of-prior .
- 17 September 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Imaging Sciences
- Vol. 18 (3) , 1929-1962
Multimodal Disentanglement by Latent Variable Separation with Surrogate Modal Specifics and Mixture-of-Distributions Priors
The multimodal variational autoencoder (VAE) is a probabilistic latent variable model for modeling the generative process of multiple modalities. Existing multimodal VAEs typically divide the latent variable into two types of variables, aiming to represent shared information across modalities and specific information for each modality. However, previous models lack a mechanism to ensure the disentanglement of these two latent variables, causing degraded generation coherence and quality. Failing in disentanglement hampers their performances, particularly concerning the unconditional coherence metric. Further, since these models are derived from VAE, they inherently struggle to generate high-quality samples. In this work, a new probabilistic latent variable model, named multimodal VAE with mixture-of-distributions prior (MVP), is proposed to address these issues. A mixture of conditional distributions is used as priors for the two latent variables separately, while each mixture component is conditioned on learnable pseudoinputs. These pseudoinputs function as prototypes for modal-specific information, which are parameters of the prior for modal-specific latent variables. Experiments conducted on the PolyMNIST and Tri-modal Fashion-MNIST datasets show that MVP outperforms all previous models in terms of generation coherence and quality. Furthermore, experiments confirm that MVP achieves better disentanglement between the two latent variables than that of other existing methods. An implementation of the MVP model is available at https://github.com/fan222/MVP_multimodal-vae-with-mixture-of-prior .
- 25 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Biology and Bioinformatics
- Vol. 22 (6) , 2817-2832
Nature-Inspired Meta-Heuristic Algorithms for Detecting Protein Complexes in Protein-Protein Interaction Networks: A Survey
In cells, various proteins interact to form protein-protein interaction networks. Protein complexes serve as the fundamental units that enable essential functions in biological organisms. Directly detecting protein complexes in protein-protein interaction networks using biology-based methods is costly and time-consuming. In recent years, different computational methods have emerged for identifying or predicting protein complexes within these networks. Following a comprehensive analysis of the issue, the optimization algorithm based on meta-heuristic methods has been completely executed for this specific type of challenge, which started in 2004. This paper provides a systematic survey of such meta-heuristic algorithms. Specifically, 34 related methods published between 2004 and 2024 are collected and summarized, focusing on how to model problems and design optimization algorithms, which are the key components of this survey. Our observations and analyses have revealed several limitations in existing studies and suggested potential avenues for future research.
- 25 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Biology and Bioinformatics
- Vol. 22 (6) , 2817-2832
Nature-Inspired Meta-Heuristic Algorithms for Detecting Protein Complexes in Protein-Protein Interaction Networks: A Survey
In cells, various proteins interact to form protein-protein interaction networks. Protein complexes serve as the fundamental units that enable essential functions in biological organisms. Directly detecting protein complexes in protein-protein interaction networks using biology-based methods is costly and time-consuming. In recent years, different computational methods have emerged for identifying or predicting protein complexes within these networks. Following a comprehensive analysis of the issue, the optimization algorithm based on meta-heuristic methods has been completely executed for this specific type of challenge, which started in 2004. This paper provides a systematic survey of such meta-heuristic algorithms. Specifically, 34 related methods published between 2004 and 2024 are collected and summarized, focusing on how to model problems and design optimization algorithms, which are the key components of this survey. Our observations and analyses have revealed several limitations in existing studies and suggested potential avenues for future research.
- 16 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. PP (1089778X) , 1
Neuro-PLS: A Generalizable Local Search Framework for Multi-objective Combinatorial Optimization
In this paper, we present a novel neural multi-objective combinatorial optimization framework with generalization ability across problems. The main idea is to integrate the framework of Pareto Local Search (PLS), a well-known problem independent multi-objective heuristic, with the concept of learning-to-optimize (L2O). In the proposed framework, namely Neuro-PLS, the backbone of PLS is guided by two neural networks to utilize cross-problem knowledge. Specifically, in Neuro-PLS, the solution-selection component is guided by a Graph Neural Network (GNN) and the neighborhood-exploration component is guided by a multi-layer perception. In the experimental studies, the training set of Neuro-PLS contains only one 200-dimensional multi-objective unconstrained binary quadratic programming (mUBQP) instance. The trained Neuro-PLS shows remarkable efficiency on optimizing large-size mUBQP instances and middle-size multi-objective traveling salesman problem (mTSP) instances with different number of objectives. Extensive experiments on a variety of mUBQP and mTSP instances show that the trained Neuro-PLS significantly outperforms some recently proposed reinforcement learning-based methods.
- 16 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. PP (1089778X) , 1
Neuro-PLS: A Generalizable Local Search Framework for Multi-objective Combinatorial Optimization
In this paper, we present a novel neural multi-objective combinatorial optimization framework with generalization ability across problems. The main idea is to integrate the framework of Pareto Local Search (PLS), a well-known problem independent multi-objective heuristic, with the concept of learning-to-optimize (L2O). In the proposed framework, namely Neuro-PLS, the backbone of PLS is guided by two neural networks to utilize cross-problem knowledge. Specifically, in Neuro-PLS, the solution-selection component is guided by a Graph Neural Network (GNN) and the neighborhood-exploration component is guided by a multi-layer perception. In the experimental studies, the training set of Neuro-PLS contains only one 200-dimensional multi-objective unconstrained binary quadratic programming (mUBQP) instance. The trained Neuro-PLS shows remarkable efficiency on optimizing large-size mUBQP instances and middle-size multi-objective traveling salesman problem (mTSP) instances with different number of objectives. Extensive experiments on a variety of mUBQP and mTSP instances show that the trained Neuro-PLS significantly outperforms some recently proposed reinforcement learning-based methods.
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 791-799
Evo-SINDy: Universal Discovery of Partial Differential Equations Using Cooperative Evolutionary Computation
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 791-799
Open AccessEvo-SINDy: Universal Discovery of Partial Differential Equations Using Cooperative Evolutionary Computation