Yijing Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yijing Liu has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Gang Feng
National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China
10 shared publications - Shuang Qin
National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu, China
6 shared publications - Xinyi Xu
National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China
4 shared publications - Hongyang Du
The University of Hong Kong
3 shared publications - Jian Wang
National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Xiaoqian Li
National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications
Latest Publications
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 6293-6308
Joint Communication Topology Reconstruction and Parameter Filtering for Heterogeneous Decentralized Federated Learning
Federated learning (FL) has been strongly promoted in wireless edge networks because it facilitates collaborative training of machine learning models while ensuring the privacy and security of individual user data. Among different FL frameworks, Decentralized Federated Learning (DFL) framework offers greater flexibility and broader applicability compared to traditional Centralized Federated Learning (CFL) framework. However, existing DFL framework fails to accommodate the heterogeneity of multi-dimensional resources (e.g., communication and computing resources), and further suffer from high communication overhead. These limitations result in reduced training efficiency. To address these issues, this paper proposes SoloDFL, a framework integrating heterogeneity-aware communication topology reconstruction and parameter filtering. In SoloDFL, each client communicates with only one neighboring client, constructing a one-on-one communication topology, and exchanges only filtered local model parameters during communication. By doing so, SoloDFL copes with the synchronization barriers caused by system heterogeneity and further reduces communication overhead. The convergence of SoloDFL is proved theoretically. Extensive experiments show that SoloDFL achieves up to a $3.9\times $ acceleration and reduces communication costs by an average of 20.5% compared to the benchmark algorithms.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 12, 6293-6308
Joint Communication Topology Reconstruction and Parameter Filtering for Heterogeneous Decentralized Federated Learning
Federated learning (FL) has been strongly promoted in wireless edge networks because it facilitates collaborative training of machine learning models while ensuring the privacy and security of individual user data. Among different FL frameworks, Decentralized Federated Learning (DFL) framework offers greater flexibility and broader applicability compared to traditional Centralized Federated Learning (CFL) framework. However, existing DFL framework fails to accommodate the heterogeneity of multi-dimensional resources (e.g., communication and computing resources), and further suffer from high communication overhead. These limitations result in reduced training efficiency. To address these issues, this paper proposes SoloDFL, a framework integrating heterogeneity-aware communication topology reconstruction and parameter filtering. In SoloDFL, each client communicates with only one neighboring client, constructing a one-on-one communication topology, and exchanges only filtered local model parameters during communication. By doing so, SoloDFL copes with the synchronization barriers caused by system heterogeneity and further reduces communication overhead. The convergence of SoloDFL is proved theoretically. Extensive experiments show that SoloDFL achieves up to a $3.9\times $ acceleration and reduces communication costs by an average of 20.5% compared to the benchmark algorithms.
- 10 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (2) , 2691-2706
Joint Inference Offloading and Model Caching for Small and Large Language Model Collaboration
Large Language Models (LLMs), with advanced content creation and inference capabilities, can provide immersive intelligent services to users in mobile edge networks. However, the increasing demand for real-time artificial intelligence (AI) applications aggravates the limitations of cloud-based LLMs due to the long response time. Meanwhile, Small Language Models (SLMs), which are cost-effective and locally deployable for terminal devices, can serve as an efficient supplement to LLMs for performing latency-sensitive tasks with lower generalization capability. Due to the resource constraints of edge networks and the diverse requirements of user tasks, it is critical to design an inference framework that effectively coordinates the deployment and collaboration of LLMs and SLMs. In this paper, we propose an LLM-SLM collaborative inference (LSCI) scheme under a mobile edge computing (MEC) architecture, which jointly decides where to cache models and how to offload inference tasks to balance latency, accuracy, and resource costs. To optimize inference performance subject to resource constraints, we jointly solve the inference task offloading and model caching problem in LSCI scheme. Specifically, we employ deep reinforcement learning (DRL) to select highly popular SLMs to be cached on the edge server, and distributed belief propagation technique to solve the associated inference task offloading issue. Numerical results show that the proposed LSCI scheme can achieve significant performance gain in terms of inference performance when compared with a number of baseline solutions.
- 10 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (2) , 2691-2706
Joint Inference Offloading and Model Caching for Small and Large Language Model Collaboration
Large Language Models (LLMs), with advanced content creation and inference capabilities, can provide immersive intelligent services to users in mobile edge networks. However, the increasing demand for real-time artificial intelligence (AI) applications aggravates the limitations of cloud-based LLMs due to the long response time. Meanwhile, Small Language Models (SLMs), which are cost-effective and locally deployable for terminal devices, can serve as an efficient supplement to LLMs for performing latency-sensitive tasks with lower generalization capability. Due to the resource constraints of edge networks and the diverse requirements of user tasks, it is critical to design an inference framework that effectively coordinates the deployment and collaboration of LLMs and SLMs. In this paper, we propose an LLM-SLM collaborative inference (LSCI) scheme under a mobile edge computing (MEC) architecture, which jointly decides where to cache models and how to offload inference tasks to balance latency, accuracy, and resource costs. To optimize inference performance subject to resource constraints, we jointly solve the inference task offloading and model caching problem in LSCI scheme. Specifically, we employ deep reinforcement learning (DRL) to select highly popular SLMs to be cached on the edge server, and distributed belief propagation technique to solve the associated inference task offloading issue. Numerical results show that the proposed LSCI scheme can achieve significant performance gain in terms of inference performance when compared with a number of baseline solutions.
- 8 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 1569-1585
Split Learning Based Cloud-Edge-End Collaborative Model Training in Heterogeneous Networks
Large language models (LLMs) demonstrate significant potential for enabling intelligent endogenous networks owing to their amazing intelligence level. LLMs are currently deployed on cloud servers as their vast parameter scales introduce a substantial computational burden to pre-training and inference processes. This deployment paradigm faces severe challenges, including insufficient personalization, high inference latency, and privacy concerns, as an increasing number of mobile users enjoy the LLM services. To enhance the personalization of pre-trained LLMs, exploiting massive local datasets distributed across edge devices to fine-tune LLMs is essential. In this paper, we propose a split learning-based cloud-edge-end collaborative training framework (SCCT) to harness the abundant computational resources of cloud and edge servers while exploiting massive distributed datasets on edge devices for LLM fine-tuning. In SCCT, an LLM with a parameter-efficient fine-tuning module is deployed on the cloud server, while a small-scale language model (SLM) is deployed across each edge device participating in SCCT and its associated edge server in the manner of split learning. SLM and LLM collaborate in a serial manner for training and inference. To optimize the collaboration efficiency, we formulate a mixed integer nonlinear programming problem to minimize the training latency of SCCT, considering the resource heterogeneity of edge devices and network dynamics. To solve this problem, a two-timescale optimization algorithm is proposed to determine the optimal split points on the large timescale and the allocation of communication and computational resources of the edge server on the small timescale. Numerical results demonstrate that the proposed two-timescale optimization algorithm assisted SCCT outperforms the state-of-the-art LLMs deployment and training paradigm in terms of training efficiency and inference performance.
- 8 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 1569-1585
Split Learning Based Cloud-Edge-End Collaborative Model Training in Heterogeneous Networks
Large language models (LLMs) demonstrate significant potential for enabling intelligent endogenous networks owing to their amazing intelligence level. LLMs are currently deployed on cloud servers as their vast parameter scales introduce a substantial computational burden to pre-training and inference processes. This deployment paradigm faces severe challenges, including insufficient personalization, high inference latency, and privacy concerns, as an increasing number of mobile users enjoy the LLM services. To enhance the personalization of pre-trained LLMs, exploiting massive local datasets distributed across edge devices to fine-tune LLMs is essential. In this paper, we propose a split learning-based cloud-edge-end collaborative training framework (SCCT) to harness the abundant computational resources of cloud and edge servers while exploiting massive distributed datasets on edge devices for LLM fine-tuning. In SCCT, an LLM with a parameter-efficient fine-tuning module is deployed on the cloud server, while a small-scale language model (SLM) is deployed across each edge device participating in SCCT and its associated edge server in the manner of split learning. SLM and LLM collaborate in a serial manner for training and inference. To optimize the collaboration efficiency, we formulate a mixed integer nonlinear programming problem to minimize the training latency of SCCT, considering the resource heterogeneity of edge devices and network dynamics. To solve this problem, a two-timescale optimization algorithm is proposed to determine the optimal split points on the large timescale and the allocation of communication and computational resources of the edge server on the small timescale. Numerical results demonstrate that the proposed two-timescale optimization algorithm assisted SCCT outperforms the state-of-the-art LLMs deployment and training paradigm in terms of training efficiency and inference performance.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 783-796
Knowledge Sharing Based Fine-Tuning for Large Pre-Trained Model in Wireless Networks
Large pre-trained models (LPMs) provide essential technical support for downstream Artificial Intelligence (AI) tasks spawning under the intelligent evolution of wireless networks. Using parameter-efficient fine-tuning (PEFT) technology, LPM can effectively capture task-specific PEFT knowledge and generalize to new tasks. However, the inherent system heterogeneity of wireless networks and data across user equipments (UEs) cause the heterogeneous PEFT models. This in turn brings difficulties in combining the PEFT knowledge of users, and thus degrades the global generalization capability of LPM. Meanwhile, additional computational and communication costs will be incurred if conventional heterogeneous model training methods are used for LPM to capture the global PEFT knowledge. Therefore, effective PEFT knowledge sharing becomes crucial for exploiting the global generalization capability of LPM. In this paper, we propose a PEFT knowledge sharing based distributed fine-tuning (DFT) scheme, by aggregating heterogeneous PEFT models. In DFT, the PEFT knowledge of users is captured with low-rank adaptive (LoRA) model, where the LoRA models can be heterogeneous for different users. On this basis, we further design an aggregation and iterative learning strategy for the heterogeneous LoRA models to capture the global PEFT knowledge from downstream users. Meanwhile, users perform iterative learning based on individual reinitialized local LoRA models, so as to avoid additional communication cost in using a global LoRA model. We theoretically analyze the convergence bound of our proposed DFT scheme. The numerical results verify the effectiveness of our proposed DFT scheme in enhancing the global generalization capability of LPM while significantly reducing communication cost.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 783-796
Knowledge Sharing Based Fine-Tuning for Large Pre-Trained Model in Wireless Networks
Large pre-trained models (LPMs) provide essential technical support for downstream Artificial Intelligence (AI) tasks spawning under the intelligent evolution of wireless networks. Using parameter-efficient fine-tuning (PEFT) technology, LPM can effectively capture task-specific PEFT knowledge and generalize to new tasks. However, the inherent system heterogeneity of wireless networks and data across user equipments (UEs) cause the heterogeneous PEFT models. This in turn brings difficulties in combining the PEFT knowledge of users, and thus degrades the global generalization capability of LPM. Meanwhile, additional computational and communication costs will be incurred if conventional heterogeneous model training methods are used for LPM to capture the global PEFT knowledge. Therefore, effective PEFT knowledge sharing becomes crucial for exploiting the global generalization capability of LPM. In this paper, we propose a PEFT knowledge sharing based distributed fine-tuning (DFT) scheme, by aggregating heterogeneous PEFT models. In DFT, the PEFT knowledge of users is captured with low-rank adaptive (LoRA) model, where the LoRA models can be heterogeneous for different users. On this basis, we further design an aggregation and iterative learning strategy for the heterogeneous LoRA models to capture the global PEFT knowledge from downstream users. Meanwhile, users perform iterative learning based on individual reinitialized local LoRA models, so as to avoid additional communication cost in using a global LoRA model. We theoretically analyze the convergence bound of our proposed DFT scheme. The numerical results verify the effectiveness of our proposed DFT scheme in enhancing the global generalization capability of LPM while significantly reducing communication cost.
- 2 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-16
Trusted Clustering Based Federated Learning in Edge Networks
Federated learning (FL) is integral to advancing edge intelligence by enabling collaborative machine learning. In FL-empowered edge networks, computing nodes first train local models and then send them to an or multiple aggregation node(s) for global model collaboration. However, the trustworthiness of both local and global models in conventional FL frameworks is compromised due to inadequate model security and transparency. Distributed ledger technique (DLT) can address this issue by leveraging multi-nodes trust capabilities to support distributed consensus. However, model training and consensus performance of DLT may significantly degrade due to instability and resource constraints of edge networks. Sharding technique provides an effective approach by dividing the ledger into smaller and manageable shards. In this paper, to improve model training and consensus performance, we propose a trusted FL framework by incorporating sharding DLT into FL frameworks. We construct a theoretical model to investigate the relationship between model training performance, consensus efficiency, and capacity of edge nodes regarding storage, computing and communications. Based on the theoretical model, we propose a trusted clustering scheme to aggregate local models. Numerical results show that our proposed scheme significantly improves network throughput for transmitting models while guaranteeing model learning performance in comparison with some classical baselines.
- 2 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-16
Trusted Clustering Based Federated Learning in Edge Networks
Federated learning (FL) is integral to advancing edge intelligence by enabling collaborative machine learning. In FL-empowered edge networks, computing nodes first train local models and then send them to an or multiple aggregation node(s) for global model collaboration. However, the trustworthiness of both local and global models in conventional FL frameworks is compromised due to inadequate model security and transparency. Distributed ledger technique (DLT) can address this issue by leveraging multi-nodes trust capabilities to support distributed consensus. However, model training and consensus performance of DLT may significantly degrade due to instability and resource constraints of edge networks. Sharding technique provides an effective approach by dividing the ledger into smaller and manageable shards. In this paper, to improve model training and consensus performance, we propose a trusted FL framework by incorporating sharding DLT into FL frameworks. We construct a theoretical model to investigate the relationship between model training performance, consensus efficiency, and capacity of edge nodes regarding storage, computing and communications. Based on the theoretical model, we propose a trusted clustering scheme to aggregate local models. Numerical results show that our proposed scheme significantly improves network throughput for transmitting models while guaranteeing model learning performance in comparison with some classical baselines.
- 8 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 11 (3) , 1334-1356
A Survey of Integrating Generative Artificial Intelligence and 6G Mobile Services: Architectures, Solutions, Technologies and Outlooks
Generative artificial intelligence (GenAI) is rapidly driving a new phase of artificial intelligence revolution, marked by various applications such as ChatGPT, Sora and DeepSeek. With powerful capabilities in content generation, personalization and user interaction, GenAI can drive significant enhancements in various mobile services to satisfy individual user preferences. Meanwhile, mobile services offer substantial support for accessibility, functionality and intelligence of GenAI applications. However, current research on integrating GenAI and mobile services remains nascent, lacking necessary theoretical and technical support. In this survey, we break down a new vision to guide research on integrating GenAI and mobile services, aiming to improve 6G intelligence levels and enable 6G mobile networks to support the integration of GenAI and mobile services effectively. We begin by examining the necessity of integrating GenAI with 6G mobile services and exploring potential learning architectures of GenAI models within mobile networks. Next, we analyze potential solutions from two perspectives: how 6G mobile networks empower GenAI and how GenAI enables mobile services. We subsequently explore a promising use case, along with essential features and techniques, to facilitate the integration of GenAI and mobile services. Finally, we discuss future research directions, aiming at realizing intelligent 6G networks.
- 8 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive Communications and Networking
- Vol. 11 (3) , 1334-1356
A Survey of Integrating Generative Artificial Intelligence and 6G Mobile Services: Architectures, Solutions, Technologies and Outlooks
Generative artificial intelligence (GenAI) is rapidly driving a new phase of artificial intelligence revolution, marked by various applications such as ChatGPT, Sora and DeepSeek. With powerful capabilities in content generation, personalization and user interaction, GenAI can drive significant enhancements in various mobile services to satisfy individual user preferences. Meanwhile, mobile services offer substantial support for accessibility, functionality and intelligence of GenAI applications. However, current research on integrating GenAI and mobile services remains nascent, lacking necessary theoretical and technical support. In this survey, we break down a new vision to guide research on integrating GenAI and mobile services, aiming to improve 6G intelligence levels and enable 6G mobile networks to support the integration of GenAI and mobile services effectively. We begin by examining the necessity of integrating GenAI with 6G mobile services and exploring potential learning architectures of GenAI models within mobile networks. Next, we analyze potential solutions from two perspectives: how 6G mobile networks empower GenAI and how GenAI enables mobile services. We subsequently explore a promising use case, along with essential features and techniques, to facilitate the integration of GenAI and mobile services. Finally, we discuss future research directions, aiming at realizing intelligent 6G networks.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 12 (3) , 2217-2230
Efficient Federated Learning in Wireless Networks With Incremental Model Quantization and Uploading
Federated Learning (FL) has been widely recognized as a promising promoter for future intelligent wireless networks, by collaboratively training a global machine learning (ML) model in a privacy-preserving manner. However, the transmission of large-scale models between clients and servers is susceptible to limited communication resources. Recently proposed model quantization can reduce communication costs by compressing the amount of model data to be transmitted. These methods need to be modified when used in wireless networks with rapidly changing radio channels. In this paper, we propose a federated learning scheme with incremental model quantization and uploading mechanism, called Fed_IQ. Specifically, individual clients quantize the local model parameters to derive the base and incremental model parameters. The base model is first uploaded, while the incremental model is uploaded when the wireless link is sufficiently good. The quantization levels are also adapted to the instantaneous channel states. The server then uses only the base model or combines the base and incremental model to aggregate a more accurate global model. Experimental results show our proposed Fed_IQ can significantly reduce transmission delay and improve model accuracy in a wireless network compared with a number of known state-of-the-art algorithms.
- 26 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 12 (3) , 2217-2230
Efficient Federated Learning in Wireless Networks With Incremental Model Quantization and Uploading
Federated Learning (FL) has been widely recognized as a promising promoter for future intelligent wireless networks, by collaboratively training a global machine learning (ML) model in a privacy-preserving manner. However, the transmission of large-scale models between clients and servers is susceptible to limited communication resources. Recently proposed model quantization can reduce communication costs by compressing the amount of model data to be transmitted. These methods need to be modified when used in wireless networks with rapidly changing radio channels. In this paper, we propose a federated learning scheme with incremental model quantization and uploading mechanism, called Fed_IQ. Specifically, individual clients quantize the local model parameters to derive the base and incremental model parameters. The base model is first uploaded, while the incremental model is uploaded when the wireless link is sufficiently good. The quantization levels are also adapted to the instantaneous channel states. The server then uses only the base model or combines the base and incremental model to aggregate a more accurate global model. Experimental results show our proposed Fed_IQ can significantly reduce transmission delay and improve model accuracy in a wireless network compared with a number of known state-of-the-art algorithms.