Related references
Note: Only part of the references are listed.
Proceedings Paper
Computer Science, Artificial Intelligence
Qinbin Li et al.
Summary: Due to increasing privacy concerns and data regulations, training data has become more fragmented, forming distributed databases of multiple data silos. Federated learning (FL) has emerged as a solution to train machine learning models collaboratively without exchanging raw data. However, the heterogeneity of data distribution among parties is a common challenge in distributed databases. Previous studies lack a comprehensive understanding of the advantages and disadvantages of FL algorithms under non-IID data settings. This paper proposes comprehensive data partitioning strategies and conducts extensive experiments to evaluate state-of-the-art FL algorithms, providing insights for future studies in addressing challenges in data silos.
2022 IEEE 38TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2022)
(2022)
Article
Computer Science, Information Systems
Raneen Younis et al.
Summary: In recent years, the amount of data available from IoT devices has increased rapidly. To protect privacy, distributed machine learning solutions are needed. However, device failure data are typically imbalanced, requiring re-balancing techniques. This paper proposes a new approach called FLY-SMOTE, which rebalances data by generating synthetic data, and experimental results demonstrate its effectiveness.
Article
Computer Science, Artificial Intelligence
Chen Zhang et al.
Summary: Federated learning is a setup where multiple clients collaborate to solve machine learning problems under the coordination of a central aggregator. It reduces systematic privacy risks and costs through local computing and model transmission. This method ensures data privacy for each device and improves learning efficiency and security.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Information Systems
Changsong Jiang et al.
Summary: Privacy-preserving federated learning achieves privacy protection for user data through membership proof and the PFLM scheme, which eliminates the stringent requirements for thresholds in the original schemes. The new scheme utilizes cryptographic accumulators and a result verification algorithm based on ElGamal encryption to enhance security and correctness verification.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Yang Zhao et al.
Summary: This study introduces a federated learning system leveraging a reputation mechanism to assist home appliance manufacturers in developing a smart home system. The system involves two stages: centralized training of customer data and model sharing among manufacturers through a reputation-based mechanism.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Hardware & Architecture
Gaoyang Liu et al.
Summary: Edge computing is gaining popularity for extending cloud computing services to the network edge with lower response times and communication costs. The integration of federated learning and edge computing in the P2FEC framework allows for constructing a unified deep learning model without uploading data to a centralized server, providing stricter protection of data privacy. Membership inference attacks were used as a case study to show that the model built by this framework achieves similar prediction performance and enhances data privacy protection compared to standard edge computing.
Article
Computer Science, Information Systems
Yi Liu et al.
Summary: This article proposes a communication-efficient on-device federated learning (FL)-based deep anomaly detection framework for sensing time-series data in IIoT. The framework includes an FL framework, AMCNN-LSTM model, and gradient compression mechanism, which can improve generalization ability, accurately detect anomalies, and enhance communication efficiency.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Information Science & Library Science
Marco Fisichella
Summary: The paper introduces a unified approach, UPHED, for detecting rare and recurring events in the domain of public health using a combination of document and token-centric techniques. Experimental results show that the approach is efficient and effective in terms of document cluster quality.
INTERNATIONAL JOURNAL ON DIGITAL LIBRARIES
(2021)
Article
Immunology
Sara Dominguez-Rodriguez et al.
Summary: This study conducted a multicenter, prospective study to identify risk factors for critical disease in hospitalized children with COVID-19, and found that factors such as inflammation, cytopenia, age, comorbidities, and organ dysfunction were major risk factors for severe illness. The severity of the syndrome was directly related to the increased risk these factors conferred for critical illness. A Bayesian model was developed to predict the risk of severe COVID-19 in children.
PEDIATRIC INFECTIOUS DISEASE JOURNAL
(2021)
Article
Computer Science, Information Systems
Francesco Buccafurri et al.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2020)
Article
Engineering, Electrical & Electronic
Shashi Raj Pandey et al.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2020)
Article
Automation & Control Systems
Yunlong Lu et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2020)
Article
Computer Science, Information Systems
Yu Chen et al.
INFORMATION SCIENCES
(2020)
Article
Computer Science, Information Systems
Yi Liu et al.
IEEE INTERNET OF THINGS JOURNAL
(2020)
Article
Automation & Control Systems
Meng Hao et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2020)
Article
Computer Science, Information Systems
Yi-Ruei Chen et al.
INFORMATION SCIENCES
(2018)
Article
Mathematics, Applied
Julian Salas et al.
MATHEMATICS IN COMPUTER SCIENCE
(2018)
Article
Computer Science, Information Systems
Cynthia Dwork et al.
THEORY OF CRYPTOGRAPHY, PROCEEDINGS
(2006)
Article
Computer Science, Artificial Intelligence
P Samarati
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2001)
