Chungang Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chungang Yan has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Junli Wang
Key Laboratory of Embedded System and Service Computing (Tongji University), Ministry of Education, Shanghai, China
13 shared publications - Changjun Jiang
Lanzhou University
10 shared publications - Mingjian Guang
School of Information and Intelligent Science, Donghua University, Shanghai, China
3 shared publications - Cheng Wang
Tongji University
2 shared publications - Guanjun Liu
Department of Computer Science, Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai, China
2 shared publications - Hongda Qi
Key Laboratory of Embedded System and Service Computing, Ministry of Education, and the National (Province-Ministry Joint) Collaborative Innovation Center for Financial Network Security, Tongji University, Shanghai, China
2 shared publications
Latest Publications
- Open Access
- 18 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (8) , 1-24
GNN-LS: An Information-Enhanced Method for Label Scarcity on Graphs
Label scarcity severely hinders the performance of the node classification task on graphs. To overcome the lack of supervised information provided by labels, some work has attempted to attach a pretext task based on self-supervised learning, aiming to mine intrinsic information from the graph data itself as a complement. However, the representation learning capacity of existing methods is undermined by two main factors: (1) insufficient supervised information caused by the underutilization of limited labels and (2) the multi-view expressiveness capabilities of intrinsic information for an individual model are restricted. Therefore, we propose an information-enhanced method for label scarcity on graphs (GNN-LS). For supervised information, we develop a dual guidance strategy that effectively utilizes unlabeled nodes while considering prediction reliability to provide stronger extra supervised guidance for the model. Meanwhile, considering the possible redundancy of the model in acquiring two types of information, we construct a regularization to reduce it. Finally, to effectively expand the range of views on the intrinsic information mined, we design a multi-view integration mechanism, which determines coefficients between intrinsic information from different views according to their respective fitness for the current dataset and label rate. Comprehensive experiments show that our method achieves significant performance gains compared with its peers on seven benchmark datasets.
- 18 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (8) , 1-24
Open AccessGNN-LS: An Information-Enhanced Method for Label Scarcity on Graphs
Label scarcity severely hinders the performance of the node classification task on graphs. To overcome the lack of supervised information provided by labels, some work has attempted to attach a pretext task based on self-supervised learning, aiming to mine intrinsic information from the graph data itself as a complement. However, the representation learning capacity of existing methods is undermined by two main factors: (1) insufficient supervised information caused by the underutilization of limited labels and (2) the multi-view expressiveness capabilities of intrinsic information for an individual model are restricted. Therefore, we propose an information-enhanced method for label scarcity on graphs (GNN-LS). For supervised information, we develop a dual guidance strategy that effectively utilizes unlabeled nodes while considering prediction reliability to provide stronger extra supervised guidance for the model. Meanwhile, considering the possible redundancy of the model in acquiring two types of information, we construct a regularization to reduce it. Finally, to effectively expand the range of views on the intrinsic information mined, we design a multi-view integration mechanism, which determines coefficients between intrinsic information from different views according to their respective fitness for the current dataset and label rate. Comprehensive experiments show that our method achieves significant performance gains compared with its peers on seven benchmark datasets.
- 19 July 2026
- Published by Springer Nature
- p. 143-157
FedGalio: Safeguarding Individual Model Watermarks Against Backdoor Attacks in Federated Learning
- 19 July 2026
- Published by Springer Nature
- p. 143-157
FedGalio: Safeguarding Individual Model Watermarks Against Backdoor Attacks in Federated Learning
- 7 June 2026
- Published by Springer Nature
- p. 546-558
Relation Prototype Driven Multimodal Knowledge Graph Completion
- 7 June 2026
- Published by Springer Nature
- p. 546-558
Relation Prototype Driven Multimodal Knowledge Graph Completion
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (3) , 2161-2176
Heuristic-Guided Multi-Agent Reinforcement Learning for Computing Service Scheduling in Distributed Data Centers
With the rapid growth of computing services in distributed data centers, efficient scheduling needs to consider workload dynamics, resource fluctuations, and diverse optimization preferences while maintaining service quality and system efficiency. Multi-Agent Deep Reinforcement Learning (MADRL) offers a decentralized and adaptive paradigm that enables agents to learn local scheduling policies aligned with individual objectives while collectively improving global performance. However, existing MADRL approaches often suffer from low sample efficiency and limited generalization under dynamic and heterogeneous conditions. This paper proposes a Heuristic-guided Multi-Agent deep Reinforcement learning (H-MAR) approach for computing service scheduling. H-MAR is a novel multi-agent learning framework where heuristic functions act as structured priors to guide personalized policy optimization, and data augmentation is employed to enhance experience coverage and policy robustness. Moreover, we provide a modified Decentralized Partially Observable Markov Decision Process (Dec-POMDP) formulation to support the theoretical analysis of H-MAR. Experiments on real-world Alibaba cluster traces show that H-MAR outperforms representative baselines in the success rate of instance creation, load balancing, and energy consumption, validating its effectiveness for adaptive and robust computing service delivery.
- 21 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (3) , 2161-2176
Heuristic-Guided Multi-Agent Reinforcement Learning for Computing Service Scheduling in Distributed Data Centers
With the rapid growth of computing services in distributed data centers, efficient scheduling needs to consider workload dynamics, resource fluctuations, and diverse optimization preferences while maintaining service quality and system efficiency. Multi-Agent Deep Reinforcement Learning (MADRL) offers a decentralized and adaptive paradigm that enables agents to learn local scheduling policies aligned with individual objectives while collectively improving global performance. However, existing MADRL approaches often suffer from low sample efficiency and limited generalization under dynamic and heterogeneous conditions. This paper proposes a Heuristic-guided Multi-Agent deep Reinforcement learning (H-MAR) approach for computing service scheduling. H-MAR is a novel multi-agent learning framework where heuristic functions act as structured priors to guide personalized policy optimization, and data augmentation is employed to enhance experience coverage and policy robustness. Moreover, we provide a modified Decentralized Partially Observable Markov Decision Process (Dec-POMDP) formulation to support the theoretical analysis of H-MAR. Experiments on real-world Alibaba cluster traces show that H-MAR outperforms representative baselines in the success rate of instance creation, load balancing, and energy consumption, validating its effectiveness for adaptive and robust computing service delivery.
- Open Access
- 30 January 2025
- Published by Springer Nature in Research Square
RETRACTED: Classifier-free Graph Few-shot Learning via Label-aware Clustering
The authors have requested that this preprint be removed from Research Square.
- 30 January 2025
- Published by Springer Nature in Research Square
Open AccessRETRACTED: Classifier-free Graph Few-shot Learning via Label-aware Clustering
The authors have requested that this preprint be removed from Research Square.
- 3 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (12) , 11375-11388
DRL-Based VNF Cooperative Scheduling Framework With Priority-Weighted Delay
Effective Service Function Chains (SFCs) mapping and Virtual Network Functions (VNFs) scheduling are crucial to ensure high-quality service provision for Internet of Things (IoT) tasks. Meeting the varying demands of multiple SFCs poses a significant challenge, particularly when working with the limited resources available in edge computing networks. Most existing working focuses on uniformly mapping and scheduling service requests in a batch processing manner within a given time period, without taking the diversity and priority of VNFs into account. When there is a sudden surge in demand, the issues of VNF queueing waiting and resources imbalance become prominent. To address the mentioned issues, this paper proposes a Deep Reinforcement Learning (DRL)-based VNF cooperative scheduling framework with priority-weighted delay. In light of the urgency of VNFs with higher priorities and the limitations of available resources, we begin by modeling an average queuing delay with priority weight based on the shortest remaining time priority technique. We then formulate a mathematical optimization problem to minimize the modeled delay in VNF scheduling process while providing suitable multidimensional resources in the edge network. Finally, a DRL method with experience replay and target Q-network is designed to effectively obtain the optimal solutions of the optimization problem from experience. The experimental results show that our proposed method outperforms its peers in terms of SFC request acceptance, delay, load balance, and resource utilization.
- 3 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (12) , 11375-11388
DRL-Based VNF Cooperative Scheduling Framework With Priority-Weighted Delay
Effective Service Function Chains (SFCs) mapping and Virtual Network Functions (VNFs) scheduling are crucial to ensure high-quality service provision for Internet of Things (IoT) tasks. Meeting the varying demands of multiple SFCs poses a significant challenge, particularly when working with the limited resources available in edge computing networks. Most existing working focuses on uniformly mapping and scheduling service requests in a batch processing manner within a given time period, without taking the diversity and priority of VNFs into account. When there is a sudden surge in demand, the issues of VNF queueing waiting and resources imbalance become prominent. To address the mentioned issues, this paper proposes a Deep Reinforcement Learning (DRL)-based VNF cooperative scheduling framework with priority-weighted delay. In light of the urgency of VNFs with higher priorities and the limitations of available resources, we begin by modeling an average queuing delay with priority weight based on the shortest remaining time priority technique. We then formulate a mathematical optimization problem to minimize the modeled delay in VNF scheduling process while providing suitable multidimensional resources in the edge network. Finally, a DRL method with experience replay and target Q-network is designed to effectively obtain the optimal solutions of the optimization problem from experience. The experimental results show that our proposed method outperforms its peers in terms of SFC request acceptance, delay, load balance, and resource utilization.
- 19 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (11) , 7392-7404
Graph Convolutional Networks With Adaptive Neighborhood Awareness
Graph convolutional networks (GCNs) can quickly and accurately learn graph representations and have shown powerful performance in many graph learning domains. Despite their effectiveness, neighborhood awareness remains essential and challenging for GCNs. Existing methods usually perform neighborhood-aware steps only from the node or hop level, which leads to a lack of capability to learn the neighborhood information of nodes from both global and local perspectives. Moreover, most methods learn the nodes’ neighborhood information from a single view, ignoring the importance of multiple views. To address the above issues, we propose a multi-view adaptive neighborhood-aware approach to learn graph representations efficiently. Specifically, we propose three random feature masking variants to perturb some neighbors’ information to promote the robustness of graph convolution operators at node-level neighborhood awareness and exploit the attention mechanism to select important neighbors from the hop level adaptively. We also utilize the multi-channel technique and introduce a proposed multi-view loss to perceive neighborhood information from multiple perspectives. Extensive experiments show that our method can better obtain graph representation and has high accuracy.
- 19 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (11) , 7392-7404
Graph Convolutional Networks With Adaptive Neighborhood Awareness
Graph convolutional networks (GCNs) can quickly and accurately learn graph representations and have shown powerful performance in many graph learning domains. Despite their effectiveness, neighborhood awareness remains essential and challenging for GCNs. Existing methods usually perform neighborhood-aware steps only from the node or hop level, which leads to a lack of capability to learn the neighborhood information of nodes from both global and local perspectives. Moreover, most methods learn the nodes’ neighborhood information from a single view, ignoring the importance of multiple views. To address the above issues, we propose a multi-view adaptive neighborhood-aware approach to learn graph representations efficiently. Specifically, we propose three random feature masking variants to perturb some neighbors’ information to promote the robustness of graph convolution operators at node-level neighborhood awareness and exploit the attention mechanism to select important neighbors from the hop level adaptively. We also utilize the multi-channel technique and introduce a proposed multi-view loss to perceive neighborhood information from multiple perspectives. Extensive experiments show that our method can better obtain graph representation and has high accuracy.
- 26 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 54 (2) , 1070-1081
The Probabilistic Liveness Decision Method of Unbounded Petri Nets Based on Machine Learning
The liveness of Petri nets (PNs) means that every event can occur in any state, establishing a close relationship with the deadlock-free property of existing systems. Due to the problem of state space explosion and the infinite state space of unbounded PNs (UPNs), the time complexity and space complexity of the liveness decision are difficult to give accurate measures; at least, they are both NP-hard. Except for some particular subclasses of UPNs, there has not been an accurate method to decide the liveness of generalized UPNs. Thus, a liveness decision method from a machine learning perspective is proposed to predict probability values about UPNs’ liveness within a finite time. The method aims to learn the feature information on UPNs by deep neural networks and establish the mapping relationship between the UPNs and the liveness. First, the concept of approximating infinite space with finite states is applied to generate reachability graphs at different moments, following the firing rules of a UPN. Then, the graph convolutional network (GCN)-based reachability graph feature representation module and the gated recurrent unit (GRU)-based UPN feature representation module are designed to map the reachability graphs at different moments into the low-dimensional feature space. And the feature vector that can characterize the UPN’s liveness is obtained to decide the liveness probabilistically. Finally, three datasets, including 50000 samples, are constructed. Based on these datasets and some case studies, the experimental results validate the method’s ability to make liveness decisions for UPNs, demonstrating its strong performance in terms of effectiveness and generalization.
- 26 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 54 (2) , 1070-1081
The Probabilistic Liveness Decision Method of Unbounded Petri Nets Based on Machine Learning
The liveness of Petri nets (PNs) means that every event can occur in any state, establishing a close relationship with the deadlock-free property of existing systems. Due to the problem of state space explosion and the infinite state space of unbounded PNs (UPNs), the time complexity and space complexity of the liveness decision are difficult to give accurate measures; at least, they are both NP-hard. Except for some particular subclasses of UPNs, there has not been an accurate method to decide the liveness of generalized UPNs. Thus, a liveness decision method from a machine learning perspective is proposed to predict probability values about UPNs’ liveness within a finite time. The method aims to learn the feature information on UPNs by deep neural networks and establish the mapping relationship between the UPNs and the liveness. First, the concept of approximating infinite space with finite states is applied to generate reachability graphs at different moments, following the firing rules of a UPN. Then, the graph convolutional network (GCN)-based reachability graph feature representation module and the gated recurrent unit (GRU)-based UPN feature representation module are designed to map the reachability graphs at different moments into the low-dimensional feature space. And the feature vector that can characterize the UPN’s liveness is obtained to decide the liveness probabilistically. Finally, three datasets, including 50000 samples, are constructed. Based on these datasets and some case studies, the experimental results validate the method’s ability to make liveness decisions for UPNs, demonstrating its strong performance in terms of effectiveness and generalization.
- 9 August 2023
- Published by Springer Nature
- p. 150-163
Dynamic and Static Feature-Aware Microservices Decomposition via Graph Neural Networks
- 9 August 2023
- Published by Springer Nature
- p. 150-163
Dynamic and Static Feature-Aware Microservices Decomposition via Graph Neural Networks