Sheng Gong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sheng Gong has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Kai Hu
School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China
5 shared publications - Shanshan Jiang
School of Management Science and Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China
5 shared publications - Yaogen Li
School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China
3 shared publications - Jiasheng Wu
School of Economics and Business Management, Nanjing University of Science and Technology, Nanjing 210094, China
2 shared publications - Liguo Weng
Nanjing University of Information Science and Technology, Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing, China
2 shared publications - Min Xia
Nanjing University of Information Science and Technology
2 shared publications
Latest Publications
- 26 September 2024
- Published by Elsevier in Pattern Recognition
- Vol. 158
Federated Incremental Learning algorithm based on Topological Data Analysis
- 26 September 2024
- Published by Elsevier in Pattern Recognition
- Vol. 158
Federated Incremental Learning algorithm based on Topological Data Analysis
- Top Cited PapersOpen Access
- 11 July 2024
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 57 (8) , 1-66
An overview of implementing security and privacy in federated learning
Federated learning has received a great deal of research attention recently,with privacy protection becoming a key factor in the development of artificial intelligence. Federated learning is a special kind of distributed learning framework, which allows multiple users to participate in model training while ensuring that their privacy is not compromised; however, this paradigm is still vulnerable to security and privacy threats from various attackers. This paper focuses on the security and privacy threats related to federated learning. First, we analyse the current research and development status of federated learning through use of the CiteSpace literature search tool. Next, we describe the basic concepts and threat models, and then analyse the security and privacy vulnerabilities within current federated learning architectures. Finally, the directions of development in this area are further discussed in the context of current advanced defence solutions, for which we provide a summary and comparison.
- 11 July 2024
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 57 (8) , 1-66
Top Cited PapersOpen AccessAn overview of implementing security and privacy in federated learning
Federated learning has received a great deal of research attention recently,with privacy protection becoming a key factor in the development of artificial intelligence. Federated learning is a special kind of distributed learning framework, which allows multiple users to participate in model training while ensuring that their privacy is not compromised; however, this paradigm is still vulnerable to security and privacy threats from various attackers. This paper focuses on the security and privacy threats related to federated learning. First, we analyse the current research and development status of federated learning through use of the CiteSpace literature search tool. Next, we describe the basic concepts and threat models, and then analyse the security and privacy vulnerabilities within current federated learning architectures. Finally, the directions of development in this area are further discussed in the context of current advanced defence solutions, for which we provide a summary and comparison.
- Open Access
- 18 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 8339-8357
A Review of Anthropogenic Ground-Level Carbon Emissions Based on Satellite Data
The severity of the global warming issue emphasizes the critical importance of utilizing carbon satellite data to estimate groundlevel carbon dioxide emissions. However, existing reviews have not kept pace with the latest research developments. Therefore, this paper provides an overview of relevant work in the global carbon emissions field to address this knowledge gap. Through visual analysis using Citespace software, the paper outlines two methods for quantifying carbon dioxide: ground-level observations and satellite remote sensing. Despite the unique advantages of ground-level observations, satellite remote sensing is crucial for its extensive spatial coverage and long-term continuity in understanding carbon cycling, drawing significant attention. Additionally, the paper integrates the application of machine learning in the carbon emissions field, dividing it into two parts: direct estimation based on ground emission inventory data and estimation of ground-level carbon emissions based on carbon satellite data. This innovative approach combines satellite observational data with ground data to accurately estimate the current ground-level carbon emissions with robust spatial distribution characteristics.
- 18 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 8339-8357
Open AccessA Review of Anthropogenic Ground-Level Carbon Emissions Based on Satellite Data
The severity of the global warming issue emphasizes the critical importance of utilizing carbon satellite data to estimate groundlevel carbon dioxide emissions. However, existing reviews have not kept pace with the latest research developments. Therefore, this paper provides an overview of relevant work in the global carbon emissions field to address this knowledge gap. Through visual analysis using Citespace software, the paper outlines two methods for quantifying carbon dioxide: ground-level observations and satellite remote sensing. Despite the unique advantages of ground-level observations, satellite remote sensing is crucial for its extensive spatial coverage and long-term continuity in understanding carbon cycling, drawing significant attention. Additionally, the paper integrates the application of machine learning in the carbon emissions field, dividing it into two parts: direct estimation based on ground emission inventory data and estimation of ground-level carbon emissions based on carbon satellite data. This innovative approach combines satellite observational data with ground data to accurately estimate the current ground-level carbon emissions with robust spatial distribution characteristics.
- 7 September 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 237
FedMMD: A Federated weighting algorithm considering Non-IID and Local Model Deviation
- 7 September 2023
- Published by Elsevier in Expert Systems with Applications
- Vol. 237
FedMMD: A Federated weighting algorithm considering Non-IID and Local Model Deviation
- Open Access
- 6 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (19) , 10025
A Federated Incremental Learning Algorithm Based on Dual Attention Mechanism
Federated incremental learning best suits the changing needs of common Federal Learning (FL) tasks. In this area, the large sample client dramatically influences the final model training results, and the unbalanced features of the client are challenging to capture. In this paper, a federated incremental learning framework is designed; firstly, part of the data is preprocessed to obtain the initial global model. Secondly, to help the global model to get the importance of the features of the whole sample of each client, and enhance the performance of the global model to capture the critical information of the feature, channel attention neural network model is designed on the client side, and a federated aggregation algorithm based on the feature attention mechanism is designed on the server side. Experiments on standard datasets CIFAR10 and CIFAR100 show that the proposed algorithm accuracy has good performance on the premise of realizing incremental learning.
- 6 October 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (19) , 10025
Open AccessA Federated Incremental Learning Algorithm Based on Dual Attention Mechanism
Federated incremental learning best suits the changing needs of common Federal Learning (FL) tasks. In this area, the large sample client dramatically influences the final model training results, and the unbalanced features of the client are challenging to capture. In this paper, a federated incremental learning framework is designed; firstly, part of the data is preprocessed to obtain the initial global model. Secondly, to help the global model to get the importance of the features of the whole sample of each client, and enhance the performance of the global model to capture the critical information of the feature, channel attention neural network model is designed on the client side, and a federated aggregation algorithm based on the feature attention mechanism is designed on the server side. Experiments on standard datasets CIFAR10 and CIFAR100 show that the proposed algorithm accuracy has good performance on the premise of realizing incremental learning.