Junlin Huang
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
Junlin Huang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Amelie Chi Zhou
Hong Kong Baptist University
2 shared publications - Xiaowen Chu
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
2 shared publications - Zhenheng Tang
Hong Kong University of Science and Technology
2 shared publications - Bo Li
The Hong Kong University of Science and Technology
1 shared publication - Chuxuan Zeng
China Unicom Intelligent Manufacturing Technology and Industry (Guangdong) Company Ltd., China Unicom Greater Bay Area Innovation Institute
1 shared publication Hao Yin
Tsinghua University
1 shared publication
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (20) , 47358-47369
Stale Information Matters: Efficiently Tackling Data Heterogeneity in Asynchronous Federated Learning With Model Calibration
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (20) , 47358-47369
Stale Information Matters: Efficiently Tackling Data Heterogeneity in Asynchronous Federated Learning With Model Calibration
- Open Access
- 12 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 866-875
Bandwidth-Aware and Overlap-Weighted Compression for Communication-Efficient Federated Learning
Current data compression methods, such as sparsification in Federated Averaging (FedAvg), effectively enhance the communication efficiency of Federated Learning (FL). However, these methods encounter challenges such as the straggler problem and diminished model performance due to heterogeneous bandwidth and non-IID (Independently and Identically Distributed) data. To address these issues, we introduce a bandwidth-aware compression framework for FL, aimed at improving communication efficiency while mitigating the problems associated with non-IID data. First, our strategy dynamically adjusts compression ratios according to bandwidth, enabling clients to upload their models at a close pace, thus exploiting the otherwise wasted time to transmit more data. Second, we identify the non-overlapped pattern of retained parameters after compression, which results in diminished client update signals due to uniformly averaged weights. Based on this finding, we propose a parameter mask to adjust the client-averaging coefficients at the parameter level, thereby more closely approximating the original updates, and improving the training convergence under heterogeneous environments. Our evaluations reveal that our method significantly boosts model accuracy, with a maximum improvement of 13% over the uncompressed FedAvg. Moreover, it achieves a 3.37 × speedup in reaching the target accuracy compared to FedAvg with a Top-K compressor, demonstrating its effectiveness in accelerating convergence with compression. The integration of common compression techniques into our framework further establishes its potential as a versatile foundation for future cross-device, communication-efficient FL research, addressing critical challenges in FL and advancing the field of distributed machine learning.
- 12 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 866-875
Open AccessBandwidth-Aware and Overlap-Weighted Compression for Communication-Efficient Federated Learning
Current data compression methods, such as sparsification in Federated Averaging (FedAvg), effectively enhance the communication efficiency of Federated Learning (FL). However, these methods encounter challenges such as the straggler problem and diminished model performance due to heterogeneous bandwidth and non-IID (Independently and Identically Distributed) data. To address these issues, we introduce a bandwidth-aware compression framework for FL, aimed at improving communication efficiency while mitigating the problems associated with non-IID data. First, our strategy dynamically adjusts compression ratios according to bandwidth, enabling clients to upload their models at a close pace, thus exploiting the otherwise wasted time to transmit more data. Second, we identify the non-overlapped pattern of retained parameters after compression, which results in diminished client update signals due to uniformly averaged weights. Based on this finding, we propose a parameter mask to adjust the client-averaging coefficients at the parameter level, thereby more closely approximating the original updates, and improving the training convergence under heterogeneous environments. Our evaluations reveal that our method significantly boosts model accuracy, with a maximum improvement of 13% over the uncompressed FedAvg. Moreover, it achieves a 3.37 × speedup in reaching the target accuracy compared to FedAvg with a Top-K compressor, demonstrating its effectiveness in accelerating convergence with compression. The integration of common compression techniques into our framework further establishes its potential as a versatile foundation for future cross-device, communication-efficient FL research, addressing critical challenges in FL and advancing the field of distributed machine learning.
- 29 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
VWR-SLAM: Tightly Coupled SLAM System Based on Visible Light Positioning Landmark, Wheel Odometer, and RGB-D Camera
Visible light positioning (VLP) is a promising technology since it can provide high-accuracy indoor localization based on the existing lighting infrastructure. Most VLP systems require a prior light-emitting diode (LED) location map, termed a VLP-landmark map in this paper, for which manual surveys are costly in practical deployment at scale. What’s more, existing approaches also require dense LED deployments. In this work, we proposed a multi-sensor fusion framework, termed VWR-SLAM, which tightly fused the VLP, Wheel odometer, and RGB-D camera to achieve Simultaneous Localization And Mapping (SLAM). Our VWR-SLAM can provide accurate and robust robot localization and navigation in LED shortage/outage situations, meanwhile, constructing the 3D sparse environment map and the 3D VLP-landmark map without tedious manual measurements. The experimental results show that our proposed scheme can provide an average robot positioning accuracy of 1.81 cm and an LED mapping accuracy of 3.01 cm.
- 29 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
VWR-SLAM: Tightly Coupled SLAM System Based on Visible Light Positioning Landmark, Wheel Odometer, and RGB-D Camera
Visible light positioning (VLP) is a promising technology since it can provide high-accuracy indoor localization based on the existing lighting infrastructure. Most VLP systems require a prior light-emitting diode (LED) location map, termed a VLP-landmark map in this paper, for which manual surveys are costly in practical deployment at scale. What’s more, existing approaches also require dense LED deployments. In this work, we proposed a multi-sensor fusion framework, termed VWR-SLAM, which tightly fused the VLP, Wheel odometer, and RGB-D camera to achieve Simultaneous Localization And Mapping (SLAM). Our VWR-SLAM can provide accurate and robust robot localization and navigation in LED shortage/outage situations, meanwhile, constructing the 3D sparse environment map and the 3D VLP-landmark map without tedious manual measurements. The experimental results show that our proposed scheme can provide an average robot positioning accuracy of 1.81 cm and an LED mapping accuracy of 3.01 cm.