Jinliang Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jinliang Yuan has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Mengwei Xu
Beijing University of Posts and Telecommunications
5 shared publications - Shangguang Wang
Beijing University of Posts and Telecommunications
5 shared publications - Chen Yang
Southwest Jiaotong University
3 shared publications - Xuanzhe Liu
Peking University
3 shared publications - Daliang Xu
Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications - Dongqi Cai
Beijing University of Posts and Telecommunications, Beijing, China
2 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (12) , 22835-22848
Communication-Efficient Satellite-Ground Federated Learning Over Intermittent LEO Satellite Networks
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (12) , 22835-22848
Communication-Efficient Satellite-Ground Federated Learning Over Intermittent LEO Satellite Networks
- Open Access
- 11 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 7-13
RTSG-SLAM: Towards Real-Time Semantic Gaussian SLAM for Vision-Language Navigation
- 11 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 7-13
Open AccessRTSG-SLAM: Towards Real-Time Semantic Gaussian SLAM for Vision-Language Navigation
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (5) , 6231-6244
Training With Integer-Only Arithmetic: Energy-Efficient Federated Learning With Mobile DSP Offloading
AI is making mobile applications increasingly cooler, but also introduces serious privacy risks due to the extensive user data collection. Federated learning (FL), as a privacy-preserving machine learning paradigm, enables mobile devices to collaboratively learn a shared prediction model while keeping all training data on devices. However, a key obstacle towards practical cross-device FL training is the huge energy consumption, especially for lightweight mobile devices. Prior literature mostly optimizes the convergence speed and network communication cost. In this work, we first perform the experimental analysis of improving FL performance through low-precision training with energy-friendly Digital Signal Processor (DSP) on mobile devices. Then, we demonstrate that directly integrating the state-of-the-art INT8 (8-bit integer) training algorithm and classic FL protocols will significantly degrade the model accuracy. Finally, we propose a novel FL protocol, namely Q-FedUpdate, incorporates two critical techniques: error-compensated aggregation and pipelined batch quantization. The former can ensure the tiny model updates be accumulated and take effects, and the latter can improve the DSP cache hit rate to reduce the context switching. Extensive experiments show that, Q-FedUpdate can effectively reduce the on-device energy consumption by 21×, and accelerate the FL convergence by 6.1× with only 2% accuracy loss.
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (5) , 6231-6244
Training With Integer-Only Arithmetic: Energy-Efficient Federated Learning With Mobile DSP Offloading
AI is making mobile applications increasingly cooler, but also introduces serious privacy risks due to the extensive user data collection. Federated learning (FL), as a privacy-preserving machine learning paradigm, enables mobile devices to collaboratively learn a shared prediction model while keeping all training data on devices. However, a key obstacle towards practical cross-device FL training is the huge energy consumption, especially for lightweight mobile devices. Prior literature mostly optimizes the convergence speed and network communication cost. In this work, we first perform the experimental analysis of improving FL performance through low-precision training with energy-friendly Digital Signal Processor (DSP) on mobile devices. Then, we demonstrate that directly integrating the state-of-the-art INT8 (8-bit integer) training algorithm and classic FL protocols will significantly degrade the model accuracy. Finally, we propose a novel FL protocol, namely Q-FedUpdate, incorporates two critical techniques: error-compensated aggregation and pipelined batch quantization. The former can ensure the tiny model updates be accumulated and take effects, and the latter can improve the DSP cache hit rate to reduce the context switching. Extensive experiments show that, Q-FedUpdate can effectively reduce the on-device energy consumption by 21×, and accelerate the FL convergence by 6.1× with only 2% accuracy loss.
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1358-1363
Evaluating Large Language Models in Traditional Chinese Medicine with Enhanced Misinformation Detection
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1358-1363
Open AccessEvaluating Large Language Models in Traditional Chinese Medicine with Enhanced Misinformation Detection
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1382-1387
TCM-Align: Curriculum-Aligned MCQ Generation for Traditional Chinese Medicine
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1382-1387
Open AccessTCM-Align: Curriculum-Aligned MCQ Generation for Traditional Chinese Medicine
- Open Access
- 29 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 279-295
Mobile Foundation Model as Firmware
- 29 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 279-295
Open AccessMobile Foundation Model as Firmware
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 2786-2794
Towards Energy-efficient Federated Learning via INT8-based Training on Mobile DSPs
AI is making the Web an even cooler place, but also introduces serious privacy risks due to the extensive user data collection. Federated learning (FL), as a privacy-preserving machine learning paradigm, enables mobile devices to collaboratively learn a shared prediction model while keeping all training data on devices. However, a key obstacle towards practical cross-device FL training is huge energy consumption, especially for lightweight mobile devices. In this work, we perform the first-of-its-kind analysis of improving FL performance through low-precision training with an energy-friendly Digital Signal Processor (DSP) on mobile devices. We first demonstrate that directly integrating the state-of-the-art INT8 (8-bit integer) training algorithm and classic FL protocols will significantly degrade the model accuracy. Moreover, we observe that there are still unavoidable frequent quantization operations on devices that cause extreme load stress on DSP-enabled INT8 training. To address the above challenges, we present Q-FedUpdate, an FL framework that efficiently preserves model accuracy with ultra-low energy consumption. It maintains a global full-precision model and allows the tiny model updates to be continuously accumulated, instead of being erased by the quantization. Furthermore, it introduces pipelining technology to parallel CPU-based quantization and DSP-enabled training, which reduces the floating-point computation overhead of frequent data quantization. Extensive experiments show that Q-FedUpdate can effectively reduce the on-device energy consumption by 21×, and accelerate the FL convergence by 6.1× with only 2% accuracy loss.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 2786-2794
Open AccessTowards Energy-efficient Federated Learning via INT8-based Training on Mobile DSPs
AI is making the Web an even cooler place, but also introduces serious privacy risks due to the extensive user data collection. Federated learning (FL), as a privacy-preserving machine learning paradigm, enables mobile devices to collaboratively learn a shared prediction model while keeping all training data on devices. However, a key obstacle towards practical cross-device FL training is huge energy consumption, especially for lightweight mobile devices. In this work, we perform the first-of-its-kind analysis of improving FL performance through low-precision training with an energy-friendly Digital Signal Processor (DSP) on mobile devices. We first demonstrate that directly integrating the state-of-the-art INT8 (8-bit integer) training algorithm and classic FL protocols will significantly degrade the model accuracy. Moreover, we observe that there are still unavoidable frequent quantization operations on devices that cause extreme load stress on DSP-enabled INT8 training. To address the above challenges, we present Q-FedUpdate, an FL framework that efficiently preserves model accuracy with ultra-low energy consumption. It maintains a global full-precision model and allows the tiny model updates to be continuously accumulated, instead of being erased by the quantization. Furthermore, it introduces pipelining technology to parallel CPU-based quantization and DSP-enabled training, which reduces the floating-point computation overhead of frequent data quantization. Extensive experiments show that Q-FedUpdate can effectively reduce the on-device energy consumption by 21×, and accelerate the FL convergence by 6.1× with only 2% accuracy loss.
- 26 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (9) , 8999-9011
Communication-Efficient Satellite-Ground Federated Learning Through Progressive Weight Quantization
Large constellations of Low Earth Orbit (LEO) satellites have been launched for Earth observation and satellite-ground communication, which collect massive imagery and sensor data. These data can enhance the AI capabilities of satellites to address global challenges such as real-time disaster navigation and mitigation. Prior studies proposed leveraging federated learning (FL) across satellite-ground to collaboratively train a share machine learning (ML) model in a privacy-preserving mechanism. However, they mostly focus on single unique challenges such as limited ground-to-satellite bandwidth, short connection window, and long connection cycle, while ignoring the completeness of these challenges in deploying efficient FL frameworks in space. In this paper, we propose an efficient satellite-ground FL framework, SatelliteFL, to address these three challenges collectively. Its key idea is to ensure that each satellite must complete per-round training within each connection window. Moreover, we design a progressive block-wise quantization algorithm that determines a unique bitwidth for each block of the ML model to maximize the model utility while not exceeding the connection window. We evaluate SatelliteFL by plugging an implemented FL platform into real-world satellite networks and satellite images. The results show that SatelliteFL highly accelerates the convergence by up to 2.8× and improves the bandwidth utilization ratio by up to 9.3× compared to the state-of-the-art methods.
- 26 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (9) , 8999-9011
Communication-Efficient Satellite-Ground Federated Learning Through Progressive Weight Quantization
Large constellations of Low Earth Orbit (LEO) satellites have been launched for Earth observation and satellite-ground communication, which collect massive imagery and sensor data. These data can enhance the AI capabilities of satellites to address global challenges such as real-time disaster navigation and mitigation. Prior studies proposed leveraging federated learning (FL) across satellite-ground to collaboratively train a share machine learning (ML) model in a privacy-preserving mechanism. However, they mostly focus on single unique challenges such as limited ground-to-satellite bandwidth, short connection window, and long connection cycle, while ignoring the completeness of these challenges in deploying efficient FL frameworks in space. In this paper, we propose an efficient satellite-ground FL framework, SatelliteFL, to address these three challenges collectively. Its key idea is to ensure that each satellite must complete per-round training within each connection window. Moreover, we design a progressive block-wise quantization algorithm that determines a unique bitwidth for each block of the ML model to maximize the model utility while not exceeding the connection window. We evaluate SatelliteFL by plugging an implemented FL platform into real-world satellite networks and satellite images. The results show that SatelliteFL highly accelerates the convergence by up to 2.8× and improves the bandwidth utilization ratio by up to 9.3× compared to the state-of-the-art methods.
- 7 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. PP, 1-11
Resource-Aware Federated Neural Architecture Search over Heterogeneous Mobile Devices
Federated learning has been recently proposed for many clients to collaboratively train a machine learning model in a privacy-preserving manner. However, it also amplifies the difficulty in designing good neural network architecture, especially considering heterogeneous mobile devices. To this end, we propose a novel neural architecture search algorithm, namely FedNAS, which can automatically generate a set of optimal models under federated settings. The main idea is to decouple the two primary steps of the NAS process, i.e, model search and model training, and separately distribute them on the cloud and devices. It also tackles the primary challenge of limited on-device computational and communication resources through its novel designs: FedNAS fully exploits the key opportunity of insufficient model candidate re-training during the architecture search process and incorporates three key optimizations: parallel candidate training on partial clients, early dropping candidates with inferior performance, and dynamic round numbers. Evaluated on typical CNN architectures and large-scale datasets, FedNAS is able to achieve comparable model accuracy as a state-of-the-art NAS algorithm that trains models with centralized data, and also reduces the client cost by up to 200_ or more compared to a straightforward design of federated NAS.
- 7 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. PP, 1-11
Resource-Aware Federated Neural Architecture Search over Heterogeneous Mobile Devices
Federated learning has been recently proposed for many clients to collaboratively train a machine learning model in a privacy-preserving manner. However, it also amplifies the difficulty in designing good neural network architecture, especially considering heterogeneous mobile devices. To this end, we propose a novel neural architecture search algorithm, namely FedNAS, which can automatically generate a set of optimal models under federated settings. The main idea is to decouple the two primary steps of the NAS process, i.e, model search and model training, and separately distribute them on the cloud and devices. It also tackles the primary challenge of limited on-device computational and communication resources through its novel designs: FedNAS fully exploits the key opportunity of insufficient model candidate re-training during the architecture search process and incorporates three key optimizations: parallel candidate training on partial clients, early dropping candidates with inferior performance, and dynamic round numbers. Evaluated on typical CNN architectures and large-scale datasets, FedNAS is able to achieve comparable model accuracy as a state-of-the-art NAS algorithm that trains models with centralized data, and also reduces the client cost by up to 200_ or more compared to a straightforward design of federated NAS.