Chang Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chang Liu has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Jun Zhao
Nanyang Technological University
7 shared publications - Guanjie Cheng
Zhejiang University, Hangzhou, China
2 shared publications - Liangxin Qian
Nanyang Technological University, Jurong West, Singapore
2 shared publications - Naibo Wang
Zhejiang University, Hangzhou, China, Ningbo Global Innovation Center, Zhejiang University, Ningbo, China, and Zhejiang Key Laboratory of Digital-Intelligence Service Technology, Hangzhou, China
2 shared publications - Xinkui Zhao
Zhejiang University, Hangzhou, China
2 shared publications - Yifan Zhang
Zhejiang University, Hangzhou, China
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15426-15434
MUSE: A Heterogeneity-Aware Multimedia Search Engine for Mobile SoCs
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15426-15434
Open AccessMUSE: A Heterogeneity-Aware Multimedia Search Engine for Mobile SoCs
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15416-15425
ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 15416-15425
Open AccessViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding
- 17 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 9261-9278
Novel Transform-Based Optimization for Resource Allocation and Task Offloading in Communication Networks
In wireless communication and edge computing networks, fractional programming (FP) and multiplicative programming (MP) are fundamental methodologies widely employed in solving non-convex optimization problems. Prior work introduced a remarkable method to solve non-convex functions with multiple ratios by deriving novel tight upper bounds, which we formalize as the UpperBound transform in this paper. However, the UpperBound transform faces critical limitations, particularly when directly extended to MP problems involving non-negative functions or discrete optimization variables. In this paper, we introduce a generalized transform termed the UP transform to overcome these limitations.We rigorously prove that the UP transform guarantees convergence to a Karush-Kuhn-Tucker (KKT) point for a broader class of MP problems, including scenarios where variables can be zero or discrete. We comprehensively illustrate the UP transform’s utility through two practical applications: partial task offloading in mobile edge computing, optimizing computation and energy efficiency; and user association coupled with resource allocation in heterogeneous networks, addressing mixed discrete-continuous optimization challenges. Comparative evaluations against conventional methods demonstrate superior convergence speed, efficiency, solution quality, and reduced computational complexity of the proposed UP transform based algorithms.
- 17 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 9261-9278
Novel Transform-Based Optimization for Resource Allocation and Task Offloading in Communication Networks
In wireless communication and edge computing networks, fractional programming (FP) and multiplicative programming (MP) are fundamental methodologies widely employed in solving non-convex optimization problems. Prior work introduced a remarkable method to solve non-convex functions with multiple ratios by deriving novel tight upper bounds, which we formalize as the UpperBound transform in this paper. However, the UpperBound transform faces critical limitations, particularly when directly extended to MP problems involving non-negative functions or discrete optimization variables. In this paper, we introduce a generalized transform termed the UP transform to overcome these limitations.We rigorously prove that the UP transform guarantees convergence to a Karush-Kuhn-Tucker (KKT) point for a broader class of MP problems, including scenarios where variables can be zero or discrete. We comprehensively illustrate the UP transform’s utility through two practical applications: partial task offloading in mobile edge computing, optimizing computation and energy efficiency; and user association coupled with resource allocation in heterogeneous networks, addressing mixed discrete-continuous optimization challenges. Comparative evaluations against conventional methods demonstrate superior convergence speed, efficiency, solution quality, and reduced computational complexity of the proposed UP transform based algorithms.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 34, 502-517
Computation and Communication Resource Optimization for Efficient Hierarchical Federated Learning
Federated Learning (FL) is a sophisticated decentralized approach in machine learning, where individual user devices perform model training locally and then transmit their parameters to a central server. This paper delves into the dynamics of a hierarchical FL system, particularly focusing on the intricate exchange of model parameters between cloud and edge servers, and between edge servers and user devices. The capacity of this hierarchical FL model to achieve predefined global model accuracy is significantly influenced by delays in communication and computation of model parameters. To address these challenges and balance the trade-off between energy consumption and execution time, we formulate a comprehensive joint computation and communication resource optimization problem. This problem is aimed at minimizing the weighted sum of FL completion time and total energy consumption, enhancing overall system efficiency. The problem is methodically decomposed into four sub-problems. The initial three sub-problems utilize fractional programming techniques to find efficient solutions that optimize resource allocation. For the final sub-problem, we employ the Concave-Convex Procedure (CCCP), which is well-suited for dealing with the non-linear aspects of the optimization challenge. We then discuss the computational complexity and give the convergence analysis of the proposed approach. Simulation results underline the effectiveness of our approach, showing faster convergence of the global model under optimized communication and computation conditions. These results clearly demonstrate the beneficial trade-off between FL completion time and energy consumption, indicating that our optimization strategy successfully enhances the performance in hierarchical federated learning systems.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 34, 502-517
Computation and Communication Resource Optimization for Efficient Hierarchical Federated Learning
Federated Learning (FL) is a sophisticated decentralized approach in machine learning, where individual user devices perform model training locally and then transmit their parameters to a central server. This paper delves into the dynamics of a hierarchical FL system, particularly focusing on the intricate exchange of model parameters between cloud and edge servers, and between edge servers and user devices. The capacity of this hierarchical FL model to achieve predefined global model accuracy is significantly influenced by delays in communication and computation of model parameters. To address these challenges and balance the trade-off between energy consumption and execution time, we formulate a comprehensive joint computation and communication resource optimization problem. This problem is aimed at minimizing the weighted sum of FL completion time and total energy consumption, enhancing overall system efficiency. The problem is methodically decomposed into four sub-problems. The initial three sub-problems utilize fractional programming techniques to find efficient solutions that optimize resource allocation. For the final sub-problem, we employ the Concave-Convex Procedure (CCCP), which is well-suited for dealing with the non-linear aspects of the optimization challenge. We then discuss the computational complexity and give the convergence analysis of the proposed approach. Simulation results underline the effectiveness of our approach, showing faster convergence of the global model under optimized communication and computation conditions. These results clearly demonstrate the beneficial trade-off between FL completion time and energy consumption, indicating that our optimization strategy successfully enhances the performance in hierarchical federated learning systems.
- Open Access
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 73-82
FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 73-82
Open AccessFedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (2) , 2527-2541
Enhancing User Experience and Energy Efficiency in Metaverse Play to Earn Games via Mobile Edge Computing
The burgeoning interest in the Metaverse has captured the attention of both academic and commercial sectors, largely due to the decentralization of the security and authenticity of digital assets. This has notably accelerated the popularity of play-to-earn (P2E) games, where participants can earn and own digital assets that are exchangeable for real-world currencies. These games, however, are computationally demanding and often not feasible on devices with limited resources, necessitating computational offloading to edge servers. Through mobile edge computing (MEC), data can be processed on Metaverse Service Provider (MSP) edge servers. A key challenge arises in balancing the latency perceived by users, which can affect gameplay, the visual experience that impacts potential earnings, and the energy consumption of user devices. Lowering the resolution of downlink transmissions can reduce latency but also diminishes visual quality, consequently affecting user earnings. To address these challenges, our research introduces a comprehensive multi-objective optimization framework that incorporates latency, visual quality, and energy consumption for Metaverse-based mobile augmented reality (MAR) games. Given the NP-hardness of this optimization challenge, we offer simple yet effective optimization algorithms to mitigate the trade-offs between delay and financial returns. Our experimental findings demonstrate that the proposed methodology effectively balances perceived latency, visual quality, and energy consumption, thereby enhancing both the user experience and the sustainability of Metaverse-based MAR systems.
- 1 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. 75 (2) , 2527-2541
Enhancing User Experience and Energy Efficiency in Metaverse Play to Earn Games via Mobile Edge Computing
The burgeoning interest in the Metaverse has captured the attention of both academic and commercial sectors, largely due to the decentralization of the security and authenticity of digital assets. This has notably accelerated the popularity of play-to-earn (P2E) games, where participants can earn and own digital assets that are exchangeable for real-world currencies. These games, however, are computationally demanding and often not feasible on devices with limited resources, necessitating computational offloading to edge servers. Through mobile edge computing (MEC), data can be processed on Metaverse Service Provider (MSP) edge servers. A key challenge arises in balancing the latency perceived by users, which can affect gameplay, the visual experience that impacts potential earnings, and the energy consumption of user devices. Lowering the resolution of downlink transmissions can reduce latency but also diminishes visual quality, consequently affecting user earnings. To address these challenges, our research introduces a comprehensive multi-objective optimization framework that incorporates latency, visual quality, and energy consumption for Metaverse-based mobile augmented reality (MAR) games. Given the NP-hardness of this optimization challenge, we offer simple yet effective optimization algorithms to mitigate the trade-offs between delay and financial returns. Our experimental findings demonstrate that the proposed methodology effectively balances perceived latency, visual quality, and energy consumption, thereby enhancing both the user experience and the sustainability of Metaverse-based MAR systems.
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (1) , 1-18
Enhancing Stability and Resource Efficiency in LLM Training for Edge-Assisted Mobile Systems
As mobile devices continue to drive advanced applications, edge computing has emerged as a crucial solution to overcome their inherent computational constraints, especially in deploying and training large language models (LLMs). Despite progress in edge computing, significant challenges remain in achieving efficient LLM training while addressing computational demands, energy consumption, and model stability. This paper presents an enhanced collaborative training framework that integrates mobile users with edge servers to optimize resource allocation. We extend the framework by incorporating model stability into the optimization objectives, mitigating performance instability often observed during distributed LLM fine-tuning. A multi-objective optimization problem is formulated to minimize energy consumption, delay, and instability, with a novel fractional programming technique and Iterative Rank Penalization (IRP) method proposed to improve the resource allocation and user-to-edge server associations. Compared to traditional methods like Semidefinite Relaxation, IRP achieves higher accuracy and computational efficiency. Extensive simulations demonstrate that our approach outperforms existing methods in reducing energy consumption and delay, and improving LLM stability across various mobile edge computing environments.
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (1) , 1-18
Enhancing Stability and Resource Efficiency in LLM Training for Edge-Assisted Mobile Systems
As mobile devices continue to drive advanced applications, edge computing has emerged as a crucial solution to overcome their inherent computational constraints, especially in deploying and training large language models (LLMs). Despite progress in edge computing, significant challenges remain in achieving efficient LLM training while addressing computational demands, energy consumption, and model stability. This paper presents an enhanced collaborative training framework that integrates mobile users with edge servers to optimize resource allocation. We extend the framework by incorporating model stability into the optimization objectives, mitigating performance instability often observed during distributed LLM fine-tuning. A multi-objective optimization problem is formulated to minimize energy consumption, delay, and instability, with a novel fractional programming technique and Iterative Rank Penalization (IRP) method proposed to improve the resource allocation and user-to-edge server associations. Compared to traditional methods like Semidefinite Relaxation, IRP achieves higher accuracy and computational efficiency. Extensive simulations demonstrate that our approach outperforms existing methods in reducing energy consumption and delay, and improving LLM stability across various mobile edge computing environments.
- Open Access
- 14 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 81-90
Resource Allocation for Stable LLM Training in Mobile Edge Computing
As mobile devices increasingly become focal points for advanced applications, edge computing presents a viable solution to their inherent computational limitations, particularly in deploying large language models (LLMs). However, despite the advancements in edge computing, significant challenges remain in efficient training and deploying LLMs due to the computational demands and data privacy concerns associated with these models. This paper explores a collaborative training framework that integrates mobile users with edge servers to optimize resource allocation, thereby enhancing both performance and efficiency. Our approach leverages parameter-efficient fine-tuning (PEFT) methods, allowing mobile users to adjust the initial layers of the LLM while edge servers handle the more demanding latter layers. Specifically, we formulate a multi-objective optimization problem to minimize the total energy consumption and delay during training. We also address the common issue of instability in model performance by incorporating stability enhancements into our objective function. Through novel fractional programming technique, we achieve a stationary point for the formulated problem. Simulations demonstrate that our method reduces the energy consumption as well as the latency, and increases the reliability of LLMs across various mobile settings.
- 14 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 81-90
Open AccessResource Allocation for Stable LLM Training in Mobile Edge Computing
As mobile devices increasingly become focal points for advanced applications, edge computing presents a viable solution to their inherent computational limitations, particularly in deploying large language models (LLMs). However, despite the advancements in edge computing, significant challenges remain in efficient training and deploying LLMs due to the computational demands and data privacy concerns associated with these models. This paper explores a collaborative training framework that integrates mobile users with edge servers to optimize resource allocation, thereby enhancing both performance and efficiency. Our approach leverages parameter-efficient fine-tuning (PEFT) methods, allowing mobile users to adjust the initial layers of the LLM while edge servers handle the more demanding latter layers. Specifically, we formulate a multi-objective optimization problem to minimize the total energy consumption and delay during training. We also address the common issue of instability in model performance by incorporating stability enhancements into our objective function. Through novel fractional programming technique, we achieve a stationary point for the formulated problem. Simulations demonstrate that our method reduces the energy consumption as well as the latency, and increases the reliability of LLMs across various mobile settings.
- 24 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (1) , 19-34
User Connection and Resource Allocation Optimization in Blockchain Empowered Metaverse Over 6G Wireless Communications
The convergence of blockchain, Metaverse, and non-fungible tokens (NFTs) brings transformative digital opportunities alongside challenges like privacy and resource management. Addressing these, we focus on optimizing user connectivity and resource allocation in an NFT-centric and blockchain-enabled Metaverse in this paper. Through user work-offloading, we optimize data tasks, user connection parameters, and server computing frequency division. In the resource allocation phase, we optimize communication-computation resource distributions, including bandwidth, transmit power, and computing frequency. We introduce the trust-cost ratio (TCR), a pivotal measure combining trust scores from users’ resources and server history with delay and energy costs. This balance ensures sustained user engagement and trust. The DASHF algorithm, central to our approach, encapsulates the Dinkelbach algorithm, alternating optimization, semidefinite relaxation (SDR), the Hungarian method, and a novel fractional programming technique from a recent IEEE JSAC paper [2]. The most challenging part of DASHF is to rewrite an optimization problem as Quadratically Constrained Quadratic Programming (QCQP) via carefully designed transformations, in order to be solved by SDR and the Hungarian algorithm. Extensive simulations validate the DASHF algorithm’s efficacy, revealing critical insights for enhancing blockchain-Metaverse applications, especially with NFTs.
- 24 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (1) , 19-34
User Connection and Resource Allocation Optimization in Blockchain Empowered Metaverse Over 6G Wireless Communications
The convergence of blockchain, Metaverse, and non-fungible tokens (NFTs) brings transformative digital opportunities alongside challenges like privacy and resource management. Addressing these, we focus on optimizing user connectivity and resource allocation in an NFT-centric and blockchain-enabled Metaverse in this paper. Through user work-offloading, we optimize data tasks, user connection parameters, and server computing frequency division. In the resource allocation phase, we optimize communication-computation resource distributions, including bandwidth, transmit power, and computing frequency. We introduce the trust-cost ratio (TCR), a pivotal measure combining trust scores from users’ resources and server history with delay and energy costs. This balance ensures sustained user engagement and trust. The DASHF algorithm, central to our approach, encapsulates the Dinkelbach algorithm, alternating optimization, semidefinite relaxation (SDR), the Hungarian method, and a novel fractional programming technique from a recent IEEE JSAC paper [2]. The most challenging part of DASHF is to rewrite an optimization problem as Quadratically Constrained Quadratic Programming (QCQP) via carefully designed transformations, in order to be solved by SDR and the Hungarian algorithm. Extensive simulations validate the DASHF algorithm’s efficacy, revealing critical insights for enhancing blockchain-Metaverse applications, especially with NFTs.
- 31 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (8) , 6290-6305
Resource Allocation of Federated Learning for the Metaverse With Mobile Augmented Reality
The Metaverse has received much attention recently. Metaverse applications via mobile augmented reality (MAR) require rapid and accurate object detection to mix digital data with the real world. Federated learning (FL) is an intriguing distributed machine learning approach due to its privacy-preserving characteristics. Due to privacy concerns and the limited computation resources on mobile devices, we incorporate FL into MAR systems of the Metaverse to train a model cooperatively. Besides, to balance the trade-off between energy, execution latency and model accuracy, thereby accommodating different demands and application scenarios, we formulate an optimization problem to minimize a weighted combination of total energy consumption, completion time and model accuracy. Through decomposing the non-convex optimization problem into two subproblems, we devise a resource allocation algorithm to determine the bandwidth allocation, transmission power, CPU frequency and video frame resolution for each participating device. We further present the convergence analysis and computational complexity of the proposed algorithm. Numerical results show that our proposed algorithm has better performance (in terms of energy consumption, completion time and model accuracy) under different weight parameters compared to existing benchmarks.
- 31 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (8) , 6290-6305
Resource Allocation of Federated Learning for the Metaverse With Mobile Augmented Reality
The Metaverse has received much attention recently. Metaverse applications via mobile augmented reality (MAR) require rapid and accurate object detection to mix digital data with the real world. Federated learning (FL) is an intriguing distributed machine learning approach due to its privacy-preserving characteristics. Due to privacy concerns and the limited computation resources on mobile devices, we incorporate FL into MAR systems of the Metaverse to train a model cooperatively. Besides, to balance the trade-off between energy, execution latency and model accuracy, thereby accommodating different demands and application scenarios, we formulate an optimization problem to minimize a weighted combination of total energy consumption, completion time and model accuracy. Through decomposing the non-convex optimization problem into two subproblems, we devise a resource allocation algorithm to determine the bandwidth allocation, transmission power, CPU frequency and video frame resolution for each participating device. We further present the convergence analysis and computational complexity of the proposed algorithm. Numerical results show that our proposed algorithm has better performance (in terms of energy consumption, completion time and model accuracy) under different weight parameters compared to existing benchmarks.