Taiyin Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Taiyin Zhao has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Tian Chen
Laboratory of Intelligent Collaborative Computing, School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China
4 shared publications Guangmin Hu
University of Electronic Science and Technology of China
2 shared publications- Aamir Mukhtar
Department of Mathematics, Faculty of Mathematics, Mohi-Ud-Din Islamic University, Nerian Sharif AJ&K, Islamabad, Pakistan
1 shared publication - Abdul Qudair Baig
Department of Mathematics and Statistics, Institute of Southern Punjab, Multan, Pakistan
1 shared publication - Bing Zhang
Laboratory of Intelligent Collaborative Computing, School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China
1 shared publication Deji Huang
CDUT
1 shared publication
Latest Publications
- Open Access
IM-GNN: Microservice Orchestration Recommendation via Interface-Matched Dependency Graphs and Graph Neural Networks
Microservice workflow orchestration recommendation aims to streamline business process construction by suggesting relevant microservices, yet existing methods relying on functional similarity in dependency graphs prove inadequate. Traditional graphs cluster functionally analogous microservices, neglecting execution-order dependencies critical for orchestration. This paper introduces a novel interface-matching-based approach to construct microservice dependency graphs, addressing the incompatibility of current methods with orchestration scenarios. The proposed method leverages a TF-WF-IDF algorithm and language models to extract input–output representations from microservice documentation, followed by interface-matching algorithms to establish call dependencies. By capturing the inherent structural symmetry in microservice interactions, where balanced and reciprocal relationships between inputs and outputs guide service connectivity, our approach enhances the fidelity of dependency graphs. Building on this graph, we present IM-GNN, a graph neural network-based recommendation model that generates microservice embeddings and computes node similarities to recommend orchestration candidates. Experiments on Amazon’s SageMaker and Comprehend datasets validate the model’s effectiveness, demonstrating superior recommendation accuracy compared to traditional methods. Key contributions include the interface-driven graph construction framework, the IM-GNN model, and empirical insights into hyperparameter impacts. This work bridges the gap between dependency graph quality and orchestration needs, offering a foundation for integrating deep learning with microservice workflow design while highlighting the role of symmetry in structuring service dependencies and optimizing orchestration patterns.
Open AccessIM-GNN: Microservice Orchestration Recommendation via Interface-Matched Dependency Graphs and Graph Neural Networks
Microservice workflow orchestration recommendation aims to streamline business process construction by suggesting relevant microservices, yet existing methods relying on functional similarity in dependency graphs prove inadequate. Traditional graphs cluster functionally analogous microservices, neglecting execution-order dependencies critical for orchestration. This paper introduces a novel interface-matching-based approach to construct microservice dependency graphs, addressing the incompatibility of current methods with orchestration scenarios. The proposed method leverages a TF-WF-IDF algorithm and language models to extract input–output representations from microservice documentation, followed by interface-matching algorithms to establish call dependencies. By capturing the inherent structural symmetry in microservice interactions, where balanced and reciprocal relationships between inputs and outputs guide service connectivity, our approach enhances the fidelity of dependency graphs. Building on this graph, we present IM-GNN, a graph neural network-based recommendation model that generates microservice embeddings and computes node similarities to recommend orchestration candidates. Experiments on Amazon’s SageMaker and Comprehend datasets validate the model’s effectiveness, demonstrating superior recommendation accuracy compared to traditional methods. Key contributions include the interface-driven graph construction framework, the IM-GNN model, and empirical insights into hyperparameter impacts. This work bridges the gap between dependency graph quality and orchestration needs, offering a foundation for integrating deep learning with microservice workflow design while highlighting the role of symmetry in structuring service dependencies and optimizing orchestration patterns.
- Open Access
- 30 March 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (7) , 3794
QMIX-GNN: A Graph Neural Network-Based Heterogeneous Multi-Agent Reinforcement Learning Model for Improved Collaboration and Decision-Making
In multi-agent reinforcement learning, the fully centralized approach suffers from issues such as explosion of the joint state and action spaces, leading to performance degradation. On the other hand, the fully decentralized approach relies on agents that focus solely on maximizing their own rewards, making effective collaboration difficult and complicating adaption to scenarios that require cooperation among multiple agents. The Centralized Training and Decentralized Execution (CTDE) framework combines both fully centralized and fully decentralized approaches. During the training phase, a virtual central node receives the observations and actions of all agents for training, while during the execution phase each agent makes decisions based only on its own observations. However, in this framework the agents do not fully consider the information of other agents or the complex interactions between them during execution, which affects the correctness of their decisions. Therefore, this paper proposes a heterogeneous multi-agent reinforcement learning model based on graph neural networks, which we call QMIX-GNN. This model efficiently and flexibly handles input data of different dimensions, enabling the fusion of heterogeneous multi-agent information and providing this fused information to the agents. In turn, this allows them to perceive more comprehensive information and improve the correctness of their decisions. Experimental results demonstrate that the QMIX-GNN model performs better than other methods on complex multi-agent collaborative tasks.
- 30 March 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (7) , 3794
Open AccessQMIX-GNN: A Graph Neural Network-Based Heterogeneous Multi-Agent Reinforcement Learning Model for Improved Collaboration and Decision-Making
In multi-agent reinforcement learning, the fully centralized approach suffers from issues such as explosion of the joint state and action spaces, leading to performance degradation. On the other hand, the fully decentralized approach relies on agents that focus solely on maximizing their own rewards, making effective collaboration difficult and complicating adaption to scenarios that require cooperation among multiple agents. The Centralized Training and Decentralized Execution (CTDE) framework combines both fully centralized and fully decentralized approaches. During the training phase, a virtual central node receives the observations and actions of all agents for training, while during the execution phase each agent makes decisions based only on its own observations. However, in this framework the agents do not fully consider the information of other agents or the complex interactions between them during execution, which affects the correctness of their decisions. Therefore, this paper proposes a heterogeneous multi-agent reinforcement learning model based on graph neural networks, which we call QMIX-GNN. This model efficiently and flexibly handles input data of different dimensions, enabling the fusion of heterogeneous multi-agent information and providing this fused information to the agents. In turn, this allows them to perceive more comprehensive information and improve the correctness of their decisions. Experimental results demonstrate that the QMIX-GNN model performs better than other methods on complex multi-agent collaborative tasks.
- 22 March 2025
- Published by Springer Nature
- p. 546-559
Enhanced Structure-Aware Graph Embedding for Workflow Recommendation
- 22 March 2025
- Published by Springer Nature
- p. 546-559
Enhanced Structure-Aware Graph Embedding for Workflow Recommendation
- Open Access
- 21 March 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (7) , 3453
Seismic Random Noise Attenuation via Low-Rank Tensor Network
Seismic data are easily contaminated by random noise, impairing subsequent geological interpretation tasks. Existing denoising methods like low-rank approximation (LRA) and deep learning (DL) show promising denoising capabilities but still have limitations; for instance, LRA performance is parameter-sensitive, and DL networks lack interpretation. As an alternative, this paper introduces the low-rank tensor network (LRTNet), an innovative approach that integrates low-rank tensor approximation (LRTA) with DL. Our method involves constructing a noise attenuation model that leverages LRTA, total variation (TV) regularization, and weighted tensor nuclear norm minimization (WTNNM). By applying the alternating direction method of multipliers (ADMM), we solve the model and transform the iterative schemes into a DL framework, where each iteration corresponds to a network layer. The key learnable parameters, including weights and thresholds, are optimized using labeled data to enhance performance. Quantitative evaluations on synthetic data reveal that LRTNet achieves an average signal-to-noise ratio (SNR) of 9.37 dB on the validation set, outperforming Pyseistr (6.46 dB) and TNN-SSTV (6.10 dB) by 45.0% and 53.6%, respectively. Furthermore, tests on real field datasets demonstrate consistent enhancements in noise suppression while preserving critical stratigraphic structures and fault discontinuities. The embedded LRTA mechanism not only improves network interpretability, but also reduces parameter sensitivity compared to conventional LRA methods. These findings position LRTNet as a robust, physics-aware solution for seismic data restoration.
- 21 March 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (7) , 3453
Open AccessSeismic Random Noise Attenuation via Low-Rank Tensor Network
Seismic data are easily contaminated by random noise, impairing subsequent geological interpretation tasks. Existing denoising methods like low-rank approximation (LRA) and deep learning (DL) show promising denoising capabilities but still have limitations; for instance, LRA performance is parameter-sensitive, and DL networks lack interpretation. As an alternative, this paper introduces the low-rank tensor network (LRTNet), an innovative approach that integrates low-rank tensor approximation (LRTA) with DL. Our method involves constructing a noise attenuation model that leverages LRTA, total variation (TV) regularization, and weighted tensor nuclear norm minimization (WTNNM). By applying the alternating direction method of multipliers (ADMM), we solve the model and transform the iterative schemes into a DL framework, where each iteration corresponds to a network layer. The key learnable parameters, including weights and thresholds, are optimized using labeled data to enhance performance. Quantitative evaluations on synthetic data reveal that LRTNet achieves an average signal-to-noise ratio (SNR) of 9.37 dB on the validation set, outperforming Pyseistr (6.46 dB) and TNN-SSTV (6.10 dB) by 45.0% and 53.6%, respectively. Furthermore, tests on real field datasets demonstrate consistent enhancements in noise suppression while preserving critical stratigraphic structures and fault discontinuities. The embedded LRTA mechanism not only improves network interpretability, but also reduces parameter sensitivity compared to conventional LRA methods. These findings position LRTNet as a robust, physics-aware solution for seismic data restoration.
- Open Access
- 14 January 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (2) , 278
3D Seismic Attribute Conditioning Using Multiscale Sheet-Enhancing Filtering
Seismic coherence attributes are valuable for identifying structural features, but they often face challenges due to significant background noise and non-feature-related stratigraphic discontinuities. To address this, it is necessary to apply attribute conditioning to the coherence to enhance the visibility of these structures. The primary challenge of attribute conditioning lies in finding a concise structural representation that isolates only the true interpretive features while effectively removing noise and stratigraphic interference. In this study, we choose sheet-like structures as this concise structural representation, as faults are typically characterized by their thin and narrow profiles. Inspired by multiscale Hessian-based filtering (MHF) and its application on vascular structure detection, we propose a method called anisotropic multiscale Hessian-based sheet-enhancing filtering (AMHSF). This method is specifically designed to extract and magnify sheet-like structures from noisy coherence images, with a novel enhancement function distinct from those traditionally used in vascular enhancement. The effectiveness of our AMHSF is demonstrated through experiments on both synthetic and real datasets, showcasing its potential to improve the identification of structural features in coherence images.
- 14 January 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (2) , 278
Open Access3D Seismic Attribute Conditioning Using Multiscale Sheet-Enhancing Filtering
Seismic coherence attributes are valuable for identifying structural features, but they often face challenges due to significant background noise and non-feature-related stratigraphic discontinuities. To address this, it is necessary to apply attribute conditioning to the coherence to enhance the visibility of these structures. The primary challenge of attribute conditioning lies in finding a concise structural representation that isolates only the true interpretive features while effectively removing noise and stratigraphic interference. In this study, we choose sheet-like structures as this concise structural representation, as faults are typically characterized by their thin and narrow profiles. Inspired by multiscale Hessian-based filtering (MHF) and its application on vascular structure detection, we propose a method called anisotropic multiscale Hessian-based sheet-enhancing filtering (AMHSF). This method is specifically designed to extract and magnify sheet-like structures from noisy coherence images, with a novel enhancement function distinct from those traditionally used in vascular enhancement. The effectiveness of our AMHSF is demonstrated through experiments on both synthetic and real datasets, showcasing its potential to improve the identification of structural features in coherence images.
- 18 May 2020
- Published by Taru Publications in Journal of Information and Optimization Sciences
- Vol. 41 (4) , 1101-1116
The eccentric based Zagreb indices of tetra sheets
Among topological descriptor, connectivity indices are very important and they have a prominent role in chemistry. The eccentric based Zagreb indices are defined as . In this article we compute the eccentric based Zagreb indices for an infinite families of tetra sheets equilateral triangular and rectangular.
- 18 May 2020
- Published by Taru Publications in Journal of Information and Optimization Sciences
- Vol. 41 (4) , 1101-1116
The eccentric based Zagreb indices of tetra sheets
Among topological descriptor, connectivity indices are very important and they have a prominent role in chemistry. The eccentric based Zagreb indices are defined as . In this article we compute the eccentric based Zagreb indices for an infinite families of tetra sheets equilateral triangular and rectangular.
- 28 January 2019
- Published by Springer Nature in Journal of Electronic Materials
- Vol. 48 (4) , 2482-2486
An All-Optical Digital 2-to-1 Multiplexer Using Photonic Crystal-Based Nonlinear Ring Resonators
- 28 January 2019
- Published by Springer Nature in Journal of Electronic Materials
- Vol. 48 (4) , 2482-2486
An All-Optical Digital 2-to-1 Multiplexer Using Photonic Crystal-Based Nonlinear Ring Resonators
- 29 October 2018
- Published by Springer Nature in Journal of Combinatorial Optimization
- Vol. 37 (4) , 1327-1341
On the 2-rainbow domination stable graphs
- 29 October 2018
- Published by Springer Nature in Journal of Combinatorial Optimization
- Vol. 37 (4) , 1327-1341
On the 2-rainbow domination stable graphs
- 4 February 2016
- Published by Springer Nature in Journal of Combinatorial Optimization
- Vol. 34 (2) , 378-382
A note on (s, t)-relaxed L(2, 1)-labeling of graphs
- 4 February 2016
- Published by Springer Nature in Journal of Combinatorial Optimization
- Vol. 34 (2) , 378-382
A note on (s, t)-relaxed L(2, 1)-labeling of graphs
- 1 March 2013
- Published by American Scientific Publishers in Journal of Computational and Theoretical Nanoscience
- Vol. 10 (3) , 651-654
A Tabu Search Algorithm for Finding k-Rainbow Domination Numbers of Graphs
- 1 March 2013
- Published by American Scientific Publishers in Journal of Computational and Theoretical Nanoscience
- Vol. 10 (3) , 651-654
A Tabu Search Algorithm for Finding k-Rainbow Domination Numbers of Graphs