Bixiao Zeng
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
Bixiao Zeng has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Xiaodong Yang
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
4 shared publications Hanchao Yu
Bureau of Frontier Sciences and Education, Chinese Academy of Sciences, Beijing, China
2 shared publications- Shubai Chen
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China
2 shared publications - Yiqiang Chen
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
2 shared publications Chunyu Hu
Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
1 shared publication- Hanlin Gu
Webank, Shenzhen, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 679-687
FedHARDA: Federated Hard-Case Cascading Annotation without Raw Data Release
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 679-687
Open AccessFedHARDA: Federated Hard-Case Cascading Annotation without Raw Data Release
- 20 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
FedAWM: Adaptive watermark allocation in non-IID federated learning
- 20 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
FedAWM: Adaptive watermark allocation in non-IID federated learning
- 1 May 2024
- Published by Springer Nature
- p. 284-296
TFAugment: A Key Frequency-Driven Data Augmentation Method for Human Activity Recognition
- 1 May 2024
- Published by Springer Nature
- p. 284-296
TFAugment: A Key Frequency-Driven Data Augmentation Method for Human Activity Recognition
- 31 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (12) , 17620-17634
Federated Data Quality Assessment Approach: Robust Learning With Mixed Label Noise
Federated learning (FL) has been an effective way to train a machine learning model distributedly, holding local data without exchanging them. However, due to the inaccessibility of local data, FL with label noise would be more challenging. Most existing methods assume only open-set or closed-set noise and correspondingly propose filtering or correction solutions, ignoring that label noise can be mixed in real-world scenarios. In this article, we propose a novel FL method to discriminate the type of noise and make the FL mixed noise-robust, named FedMIN. FedMIN employs a composite framework that captures local-global differences in multiparticipant distributions to model generalized noise patterns. By determining adaptive thresholds for identifying mixed label noise in each client and assigning appropriate weights during model aggregation, FedMIN enhances the performance of the global model. Furthermore, FedMIN incorporates a loss alignment mechanism using local and global Gaussian mixture models (GMMs) to mitigate the risk of revealing samplewise loss. Extensive experiments are conducted on several public datasets, which include the simulated FL testbeds, i.e., CIFAR-10, CIFAR-100, and SVHN, and the real-world ones, i.e., Camelyon17 and multiorgan nuclei challenge (MoNuSAC). Compared to FL benchmarks, FedMIN improves model accuracy by up to 9.9% due to its superior noise estimation capabilities.
- 31 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (12) , 17620-17634
Federated Data Quality Assessment Approach: Robust Learning With Mixed Label Noise
Federated learning (FL) has been an effective way to train a machine learning model distributedly, holding local data without exchanging them. However, due to the inaccessibility of local data, FL with label noise would be more challenging. Most existing methods assume only open-set or closed-set noise and correspondingly propose filtering or correction solutions, ignoring that label noise can be mixed in real-world scenarios. In this article, we propose a novel FL method to discriminate the type of noise and make the FL mixed noise-robust, named FedMIN. FedMIN employs a composite framework that captures local-global differences in multiparticipant distributions to model generalized noise patterns. By determining adaptive thresholds for identifying mixed label noise in each client and assigning appropriate weights during model aggregation, FedMIN enhances the performance of the global model. Furthermore, FedMIN incorporates a loss alignment mechanism using local and global Gaussian mixture models (GMMs) to mitigate the risk of revealing samplewise loss. Extensive experiments are conducted on several public datasets, which include the simulated FL testbeds, i.e., CIFAR-10, CIFAR-100, and SVHN, and the real-world ones, i.e., Camelyon17 and multiorgan nuclei challenge (MoNuSAC). Compared to FL benchmarks, FedMIN improves model accuracy by up to 9.9% due to its superior noise estimation capabilities.
- Open Access
- 21 June 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 13 (5) , 1-23
CLC: A Consensus-based Label Correction Approach in Federated Learning
Federated learning (FL) is a novel distributed learning framework where multiple participants collaboratively train a global model without sharing any raw data to preserve privacy. However, data quality may vary among the participants, the most typical of which is label noise. The incorrect label would significantly damage the performance of the global model. In FL, the inaccessibility of raw data makes this issue more challenging. Previously published studies are limited to using a task-specific benchmark-trained model to evaluate the relevance between the benchmark dataset in the server and the local one on the participants’ side. However, such approaches have failed to exploit the cooperative nature of FL itself and are not practical. This paper proposes a Consensus-based Label Correction approach (CLC) in FL, which tries to correct the noisy labels using the developed consensus method among the FL participants. The consensus-defined class-wise information is used to identify the noisy labels and correct them with pseudo-labels. Extensive experiments are conducted on several public datasets in various settings. The experimental results prove the advantage over the state-of-art methods. The link to the source code is https://github.com/bixiao-zeng/CLC.git .
- 21 June 2022
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Intelligent Systems and Technology
- Vol. 13 (5) , 1-23
Open AccessCLC: A Consensus-based Label Correction Approach in Federated Learning
Federated learning (FL) is a novel distributed learning framework where multiple participants collaboratively train a global model without sharing any raw data to preserve privacy. However, data quality may vary among the participants, the most typical of which is label noise. The incorrect label would significantly damage the performance of the global model. In FL, the inaccessibility of raw data makes this issue more challenging. Previously published studies are limited to using a task-specific benchmark-trained model to evaluate the relevance between the benchmark dataset in the server and the local one on the participants’ side. However, such approaches have failed to exploit the cooperative nature of FL itself and are not practical. This paper proposes a Consensus-based Label Correction approach (CLC) in FL, which tries to correct the noisy labels using the developed consensus method among the FL participants. The consensus-defined class-wise information is used to identify the noisy labels and correct them with pseudo-labels. Extensive experiments are conducted on several public datasets in various settings. The experimental results prove the advantage over the state-of-art methods. The link to the source code is https://github.com/bixiao-zeng/CLC.git .