Yuanzhe Geng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuanzhe Geng has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Erwu Liu
Tongji University
9 shared publications - Rui Wang
Tongji University
7 shared publications - Jie Wang
Sino-German College of Intelligent Manufacturing, Shenzhen Technology University
3 shared publications - Wei Ni
CSIRO
3 shared publications - Abbas Jamalipour
The University of Sydney
2 shared publications Xinyu Qu
School of Electronics and Information Engineering, Tongji University, Shanghai, China
2 shared publications
Latest Publications
- 20 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 6955-6969
Hierarchical Attention-Driven Multi-Agent Reinforcement Learning for Resource Allocation in Cell-Free Massive MIMO With Integrated Sensing and Communication
Cell-Free massive MIMO (CF mMIMO), as a cornerstone for future wireless communication networks, can significantly enhance spectral efficiency, reduce energy consumption, and achieve seamless coverage. This paper investigates dynamic resource allocation in CF mMIMO systems provisioning integrated sensing and communication (ISAC) and involving multiple users and heterogeneous services. To address the rapidly varying channels, high complexity, task-dependent relevance and insufficient information sharing among access points (APs) arising from ISAC requirements, we propose a novel Hierarchical Attention-Driven Multi-Agent Reinforcement Learning (HADMARL) framework. A higher-layer “Commander Controller” outputs the AP-user pairing matrix, which is passed to a lowerlayer “Worker Controller” that leverages the central attention mechanism to perform fine-grained resource allocation. Simulations demonstrate that HAD-MARL achieves about a 10% improvement in system utility score compared to benchmarks, with the performance gains becoming more pronounced as the number of APs and users increases. We empirically demonstrate and visualize the effect of the central attention mechanism on the formation of efficient collaboration among APs. The source code is available at: https://github.com/Andyyy2000/HAD.git.
- 20 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 6955-6969
Hierarchical Attention-Driven Multi-Agent Reinforcement Learning for Resource Allocation in Cell-Free Massive MIMO With Integrated Sensing and Communication
Cell-Free massive MIMO (CF mMIMO), as a cornerstone for future wireless communication networks, can significantly enhance spectral efficiency, reduce energy consumption, and achieve seamless coverage. This paper investigates dynamic resource allocation in CF mMIMO systems provisioning integrated sensing and communication (ISAC) and involving multiple users and heterogeneous services. To address the rapidly varying channels, high complexity, task-dependent relevance and insufficient information sharing among access points (APs) arising from ISAC requirements, we propose a novel Hierarchical Attention-Driven Multi-Agent Reinforcement Learning (HADMARL) framework. A higher-layer “Commander Controller” outputs the AP-user pairing matrix, which is passed to a lowerlayer “Worker Controller” that leverages the central attention mechanism to perform fine-grained resource allocation. Simulations demonstrate that HAD-MARL achieves about a 10% improvement in system utility score compared to benchmarks, with the performance gains becoming more pronounced as the number of APs and users increases. We empirically demonstrate and visualize the effect of the central attention mechanism on the formation of efficient collaboration among APs. The source code is available at: https://github.com/Andyyy2000/HAD.git.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 10496-10514
Privacy-Preserving Consensus-Oriented Aggregation for Federated Learning With Heterogeneity
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 10496-10514
Privacy-Preserving Consensus-Oriented Aggregation for Federated Learning With Heterogeneity
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 10 (6) , 2193-2208
Balancing Performance and Cost for Two-Hop Cooperative Communications: Stackelberg Game and Distributed Multi-Agent Reinforcement Learning
This paper aims to balance performance and cost in a two-hop wireless cooperative communication network where the source and relays have contradictory optimization goals and make decisions in a distributed manner. This differs from most existing works that have typically assumed that source and relay nodes follow a schedule created implicitly by a central controller. We propose that the relays form an alliance in an attempt to maximize the benefit of relaying while the source aims to increase the channel capacity cost-effectively. To this end, we establish the trade problem as a Stackelberg game, and prove the existence of its equilibrium. Another important aspect is that we use multi-agent reinforcement learning (MARL) to approach the equilibrium in a situation where the instantaneous channel state information (CSI) is unavailable, and the source and relays do not have knowledge of each other’s goal. A multi-agent deep deterministic policy gradient-based framework is designed, where the relay alliance and the source act as agents. Experiments demonstrate that the proposed method can obtain an acceptable performance that is close to the game-theoretic equilibrium for all players under time-invariant environments, which considerably outperforms its potential alternatives and is only about 2.9% away from the optimal solution.
- 13 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 10 (6) , 2193-2208
Balancing Performance and Cost for Two-Hop Cooperative Communications: Stackelberg Game and Distributed Multi-Agent Reinforcement Learning
This paper aims to balance performance and cost in a two-hop wireless cooperative communication network where the source and relays have contradictory optimization goals and make decisions in a distributed manner. This differs from most existing works that have typically assumed that source and relay nodes follow a schedule created implicitly by a central controller. We propose that the relays form an alliance in an attempt to maximize the benefit of relaying while the source aims to increase the channel capacity cost-effectively. To this end, we establish the trade problem as a Stackelberg game, and prove the existence of its equilibrium. Another important aspect is that we use multi-agent reinforcement learning (MARL) to approach the equilibrium in a situation where the instantaneous channel state information (CSI) is unavailable, and the source and relays do not have knowledge of each other’s goal. A multi-agent deep deterministic policy gradient-based framework is designed, where the relay alliance and the source act as agents. Experiments demonstrate that the proposed method can obtain an acceptable performance that is close to the game-theoretic equilibrium for all players under time-invariant environments, which considerably outperforms its potential alternatives and is only about 2.9% away from the optimal solution.
- 26 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (9) , 15359-15374
Reinforcement-Learning-Based Policy Design for Outage Minimization in DF Relaying Networks
Relay-enabled cooperative communication has been a hot topic in the area of the Internet of Things (IoT), for its help in providing important solutions to resource limitations in IoT communication scenarios. In this article, we study the outage minimization problem in a power-limited decode-and-forward (DF) relaying network with environmental uncertainty. To reduce the outage probability and improve the quality of service, existing researches usually rely on the assumption of both exact instantaneous channel state information (CSI) and environmental uncertainty. However, it is difficult to obtain perfect instantaneous CSI immediately under practical situations where channel states change rapidly, and the uncertainty in communication environments may not be observed, which makes traditional methods not applicable. Therefore, we turn to reinforcement learning (RL) methods for solutions, which do not need any prior knowledge of underlying channels or assumptions of environmental uncertainty. The RL method is to learn from the interaction with the communication environment, optimize its action policy, and then propose relay selection and power allocation schemes. In this work, we first analyze the robustness of RL action policy by giving the lower bound of the worst case performance, when RL methods are applied to communication scenarios with environment uncertainty. Then, we propose a robust algorithm for outage probability minimization based on RL. Simulation results reveal that compared to traditional RL methods without robust design, our approach has good generalization ability and can improve the worst case performance by about 4%.
- 26 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (9) , 15359-15374
Reinforcement-Learning-Based Policy Design for Outage Minimization in DF Relaying Networks
Relay-enabled cooperative communication has been a hot topic in the area of the Internet of Things (IoT), for its help in providing important solutions to resource limitations in IoT communication scenarios. In this article, we study the outage minimization problem in a power-limited decode-and-forward (DF) relaying network with environmental uncertainty. To reduce the outage probability and improve the quality of service, existing researches usually rely on the assumption of both exact instantaneous channel state information (CSI) and environmental uncertainty. However, it is difficult to obtain perfect instantaneous CSI immediately under practical situations where channel states change rapidly, and the uncertainty in communication environments may not be observed, which makes traditional methods not applicable. Therefore, we turn to reinforcement learning (RL) methods for solutions, which do not need any prior knowledge of underlying channels or assumptions of environmental uncertainty. The RL method is to learn from the interaction with the communication environment, optimize its action policy, and then propose relay selection and power allocation schemes. In this work, we first analyze the robustness of RL action policy by giving the lower bound of the worst case performance, when RL methods are applied to communication scenarios with environment uncertainty. Then, we propose a robust algorithm for outage probability minimization based on RL. Simulation results reveal that compared to traditional RL methods without robust design, our approach has good generalization ability and can improve the worst case performance by about 4%.
- 24 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (2) , 3653-3661
FedINS2: A Federated-Edge-Learning-Based Inertial Navigation System With Segment Fusion
Modern inertial measurement units (IMUs) with low cost, small size, and low power consumption are the key to improving indoor positioning accuracy. However, the performance of IMU in current mobile phones is spotty. The IMU positioning error of mainstream cell phones is basically greater than 1%, which makes it difficult for indoor fusion positioning technology to achieve accuracy within 3 m on a mobile phone, seriously restricting the development of the industry. Therefore, the existing indoor fusion algorithms need to introduce additional hardware, such as high-density UWB/Wi-Fi/Bluetooth deployment, to compensate for the lack of IMU performance, which significantly increases the deployment cost, difficulty, and reduces environmental applicability. It is found that deep learning can greatly improve the performance of IMU, but traditional deep learning methods have problems such as privacy protection, difficulty in data collection, and low training efficiency. Therefore, we propose a novel data-driven inertial navigation method based on federated learning, named FedINS, to improve IMU performance and solve the above-mentioned problems. In order to further improve performance and reduce hardware cost, we introduce the concept of segment fusion. FedINS2 (2 means the second S, which is the segment) is formed by combining FedINS with low-cost edge-end ranging, which has terminal computing capabilities and edge-end ranging capabilities. FedINS2 not only greatly improves the performance of the smartphone IMU from 3.6% to 0.8%, but also has the characteristics of privacy protection and efficient data collection. Experimental results demonstrate that the proposed data-driven inertial navigation algorithm is effective.
- 24 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (2) , 3653-3661
FedINS2: A Federated-Edge-Learning-Based Inertial Navigation System With Segment Fusion
Modern inertial measurement units (IMUs) with low cost, small size, and low power consumption are the key to improving indoor positioning accuracy. However, the performance of IMU in current mobile phones is spotty. The IMU positioning error of mainstream cell phones is basically greater than 1%, which makes it difficult for indoor fusion positioning technology to achieve accuracy within 3 m on a mobile phone, seriously restricting the development of the industry. Therefore, the existing indoor fusion algorithms need to introduce additional hardware, such as high-density UWB/Wi-Fi/Bluetooth deployment, to compensate for the lack of IMU performance, which significantly increases the deployment cost, difficulty, and reduces environmental applicability. It is found that deep learning can greatly improve the performance of IMU, but traditional deep learning methods have problems such as privacy protection, difficulty in data collection, and low training efficiency. Therefore, we propose a novel data-driven inertial navigation method based on federated learning, named FedINS, to improve IMU performance and solve the above-mentioned problems. In order to further improve performance and reduce hardware cost, we introduce the concept of segment fusion. FedINS2 (2 means the second S, which is the segment) is formed by combining FedINS with low-cost edge-end ranging, which has terminal computing capabilities and edge-end ranging capabilities. FedINS2 not only greatly improves the performance of the smartphone IMU from 3.6% to 0.8%, but also has the characteristics of privacy protection and efficient data collection. Experimental results demonstrate that the proposed data-driven inertial navigation algorithm is effective.
- 10 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 52 (1) , 134-148
A Survey of 17 Indoor Travel Assistance Systems for Blind and Visually Impaired People
Not only has information technology evolved rapidly, but the spatial cognition theory for blind and visually impaired (BVI) people has also made great strides, which has opened up a new opportunity for indoor travel assistance systems (ITASs). However, there are still some issues that have not been effectively addressed due to the lack of guidance of the spatial cognition theory. Thus, this article presents a comparative survey among ITASs proposed in the last four years in an effort to inform researchers and developers about system problems and challenges and inform BVI people about the various types and functions of the ITAS. This article will also make researchers and developers aware of the importance of the spatial cognition theory. Furthermore, we give predictions for future trends based on a detailed analysis of 17 ITASs.
- 10 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 52 (1) , 134-148
A Survey of 17 Indoor Travel Assistance Systems for Blind and Visually Impaired People
Not only has information technology evolved rapidly, but the spatial cognition theory for blind and visually impaired (BVI) people has also made great strides, which has opened up a new opportunity for indoor travel assistance systems (ITASs). However, there are still some issues that have not been effectively addressed due to the lack of guidance of the spatial cognition theory. Thus, this article presents a comparative survey among ITASs proposed in the last four years in an effort to inform researchers and developers about system problems and challenges and inform BVI people about the various types and functions of the ITAS. This article will also make researchers and developers aware of the importance of the spatial cognition theory. Furthermore, we give predictions for future trends based on a detailed analysis of 17 ITASs.
- Open Access
- 16 October 2021
- Published by Institution of Engineering and Technology (IET) in IET Blockchain
- Vol. 1 (2-4) , 105-117
Blockchain‐based indoor location paging and answering service with truncated‐geo‐indistinguishability
Indoor location‐based services have numerous applications built on indoor navigation. Over the years, researchers have proposed various indoor navigation methods to find a certain point of interest. This paper proposes location paging and answering service (LPAS) for finding out someone in an indoor environment . However, it may face serious problems of privacy disclosure of the clients' indoor location data . To ensure security, privacy and convenience, the authors leverage blockchain to model the indoor environment, and build blockchain‐based indoor LPAS (BILPAS) on blockchain by embedding our three‐way‐handshake Diffie–Hellman Key Agreement procedures. Our BILPAS can automatically establish a secure and privacy communication tunnel between any two users, thus greatly liberating participants from unnecessary self‐determining interactions . On the premise that the certain person can also be found, the authors introduce Truncated‐Geo‐Indistinguishability (TGeoI) to perturb the actual location within a limited, valid, user‐defined distance, thereby allowing users to obtain reasonable location privacy. The authors have put a strong emphasis in the formal treatment of the reasonable privacy guarantees, giving a rigorous definition of TGeoI and providing a comparison with Geo‐Indistinguishability that the authors' method satisfies such property. Then, the authors present the BILPAS prototype and implement it on Hyperledger Fabric. Finally, the authors conduct the security and privacy analysis and evaluate the time performance. The experiment results validate the reasonable privacy, high security and convenience of the authors' framework.
- 16 October 2021
- Published by Institution of Engineering and Technology (IET) in IET Blockchain
- Vol. 1 (2-4) , 105-117
Open AccessBlockchain‐based indoor location paging and answering service with truncated‐geo‐indistinguishability
Indoor location‐based services have numerous applications built on indoor navigation. Over the years, researchers have proposed various indoor navigation methods to find a certain point of interest. This paper proposes location paging and answering service (LPAS) for finding out someone in an indoor environment . However, it may face serious problems of privacy disclosure of the clients' indoor location data . To ensure security, privacy and convenience, the authors leverage blockchain to model the indoor environment, and build blockchain‐based indoor LPAS (BILPAS) on blockchain by embedding our three‐way‐handshake Diffie–Hellman Key Agreement procedures. Our BILPAS can automatically establish a secure and privacy communication tunnel between any two users, thus greatly liberating participants from unnecessary self‐determining interactions . On the premise that the certain person can also be found, the authors introduce Truncated‐Geo‐Indistinguishability (TGeoI) to perturb the actual location within a limited, valid, user‐defined distance, thereby allowing users to obtain reasonable location privacy. The authors have put a strong emphasis in the formal treatment of the reasonable privacy guarantees, giving a rigorous definition of TGeoI and providing a comparison with Geo‐Indistinguishability that the authors' method satisfies such property. Then, the authors present the BILPAS prototype and implement it on Hyperledger Fabric. Finally, the authors conduct the security and privacy analysis and evaluate the time performance. The experiment results validate the reasonable privacy, high security and convenience of the authors' framework.
- 13 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 70 (1) , 171-184
Hierarchical Reinforcement Learning for Relay Selection and Power Optimization in Two-Hop Cooperative Relay Network
In this paper, we study the outage probability minimizing problem in a two-hop cooperative relay network. To reduce outage probability, existing studies propose many schemes for relay selection and power allocation, which are usually based on the assumption of exact channel state information (CSI). However, it is difficult to obtain perfect instantaneous CSI in practical situations where channel states change rapidly, and thus traditional methods would not perform well. Considering these factors, we turn to the emerging reinforcement learning (RL) methods for solutions. RL methods do not need any prior knowledge of CSI, but use neural network for approximation and decision after interacting with communication environment. Nevertheless, conventional RL methods, including most deep reinforcement learning (DRL) methods, cannot perform well when the search space is too large. In addition, non-stationarity is a common problem when using hierarchical reinforcement learning (HRL), which is caused by the changing behavior in different hierarchies. Therefore, we first propose a DRL framework with an outage-based reward function, which is then used as a baseline. Then, we further design an HRL framework and training algorithm. By decomposing relay selection and power allocation into two hierarchical optimization objectives, and combining on- policy and off-policy methods in the HRL framework, our method successfully address the sparse reward and non-stationary problem. Simulation results reveal that compared with traditional DRL method, the proposed HRL training algorithm can converge faster and reduce the outage probability by 8% in two-hop relay network with the same outage threshold.
- 13 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 70 (1) , 171-184
Hierarchical Reinforcement Learning for Relay Selection and Power Optimization in Two-Hop Cooperative Relay Network
In this paper, we study the outage probability minimizing problem in a two-hop cooperative relay network. To reduce outage probability, existing studies propose many schemes for relay selection and power allocation, which are usually based on the assumption of exact channel state information (CSI). However, it is difficult to obtain perfect instantaneous CSI in practical situations where channel states change rapidly, and thus traditional methods would not perform well. Considering these factors, we turn to the emerging reinforcement learning (RL) methods for solutions. RL methods do not need any prior knowledge of CSI, but use neural network for approximation and decision after interacting with communication environment. Nevertheless, conventional RL methods, including most deep reinforcement learning (DRL) methods, cannot perform well when the search space is too large. In addition, non-stationarity is a common problem when using hierarchical reinforcement learning (HRL), which is caused by the changing behavior in different hierarchies. Therefore, we first propose a DRL framework with an outage-based reward function, which is then used as a baseline. Then, we further design an HRL framework and training algorithm. By decomposing relay selection and power allocation into two hierarchical optimization objectives, and combining on- policy and off-policy methods in the HRL framework, our method successfully address the sparse reward and non-stationary problem. Simulation results reveal that compared with traditional DRL method, the proposed HRL training algorithm can converge faster and reduce the outage probability by 8% in two-hop relay network with the same outage threshold.
- 14 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 10 (9) , 1969-1973
Deep Deterministic Policy Gradient for Relay Selection and Power Allocation in Cooperative Communication Network
Perfect channel state information (CSI) is usually required when considering relay selection and power allocation in cooperative communication. However, it is difficult to get an accurate CSI in practical situations. In this letter, we study the outage probability minimizing problem based on optimizing relay selection and transmission power. We propose a prioritized experience replay aided deep deterministic policy gradient learning framework, which can find an optimal solution by dealing with continuous action space, without any prior knowledge of CSI. Simulation results reveal that our approach outperforms reinforcement learning based methods in existing literatures, and improves the communication success rate by about 5%.
- 14 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 10 (9) , 1969-1973
Deep Deterministic Policy Gradient for Relay Selection and Power Allocation in Cooperative Communication Network
Perfect channel state information (CSI) is usually required when considering relay selection and power allocation in cooperative communication. However, it is difficult to get an accurate CSI in practical situations. In this letter, we study the outage probability minimizing problem based on optimizing relay selection and transmission power. We propose a prioritized experience replay aided deep deterministic policy gradient learning framework, which can find an optimal solution by dealing with continuous action space, without any prior knowledge of CSI. Simulation results reveal that our approach outperforms reinforcement learning based methods in existing literatures, and improves the communication success rate by about 5%.