Federated Learning Based on Data Divergence and Differential Privacy in燜inancial Risk Control Research
Source abstract
Abstract
In the financial sector, data are highly confidential and sensitive, and ensuring data privacy is critical. Sample fusion is the basis of horizontal federation learning, but it is suitable only for scenarios where customers have the same format but different targets, namely for scenarios with strong feature overlapping and weak user overlapping. To solve this limitation, this paper proposes a federated learning-based model with local data sharing and differential privacy. The indexing mechanism of differential privacy is used to obtain different degrees of privacy budgets, which are applied to the gradient according to the contribution degree to ensure privacy without affecting accuracy. In addition, data sharing is performed to improve the utility of the global model. Further, the distributed prediction model is used to predict customers’ loan propensity on the premise of protecting user privacy. Using an aggregation mechanism based on federated learning can help to train the model on distributed data without exposing local data. The proposed method is verified by experiments, and experimental results show that for non-iid data, the proposed method can effectively improve data accuracy and reduce the impact of sample tilt. The proposed method can be extended to edge computing, blockchain, and the Industrial Internet of Things (IIoT) fields. The theoretical analysis and experimental results show that the proposed method can ensure the privacy and accuracy of the federated learning process and can also improve the model utility for non-iid data by 7% compared to the federated averaging method (FedAvg).
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data · Privacy, Security, and Data Protection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (31)
Show source-provided references
1. Applying machine learning techniques for religious extremism detection on online user contents10.32604/cmc.2022.019189 ↗
2. Deer hunting optimization with deep learning model for lung cancer classification10.32604/cmc.2022.028856 ↗
3. Federated learning framework for mobile edge computing networks
4. Decentralised federated learning with adaptive partial gradient aggregation10.1049/trit.2020.0082 ↗
5. Predicting default risk on peer-to-peer lending imbalanced datasets10.1109/ACCESS.2021.3079701 ↗
6. Resource rationing for wireless federated learning: Concept, benefits, and challenges10.1109/MCOM.001.2000744 ↗
7. Adaptive federated learning in resource constrained edge computing systems10.1109/JSAC.2019.2904348 ↗
8. Prediction of loan status in commercial bank using machine learning classifier
9. Design of decentralized personal loaning platform based on blockchain
10. FetchSGD: Communication-efficient federated learning with sketching
11. Divide the gradient by a running average of its recent magnitude. cours-era: Neural networks for machine learning
12. J. Zhang, Y. Wu and R. Pan, “Auction-based ex-post-payment incentive mechanism design for horizontal federated learning with reputation and contribution measurement,” arXiv: 2201.02410, 2022. [Online]. Available: https://arxiv.org/abs/2201.02410.
13. Inspecting the running process of horizontal federated learning via visual analytics
14. Blockchained on-device federated learning10.1109/LCOMM.2019.2921755 ↗
15. Communication efficient learning of deep networks from decentralized data
16. Robust and communication-efficient federated learning from non-iid data10.1109/TNNLS.2019.2944481 ↗
17. Federated learning in mobile edge networks: A comprehensive survey10.1109/COMST.2020.2986024 ↗
18. Unequal error protection transmission for federated learning10.1049/cmu2.12379 ↗
19. Federated optimization in heterogeneous networks
20. LoAd-boost: Loss-based adaboost federated machine learning with reduced computational complexity on IID and non-IID intensive care data
21. F. Ongati and E. L. Muchemi, “Big data intelligence using distributed deep neural networks,” arXiv: 1909.02873, 2019. [Online]. Available: https://arxiv.org/abs/1909.02873.
22. J. Zhu and M. Blaschko, “Differentially private SGD with sparse gradients,” arXiv: 2112.00845, 2021. [Online]. Available: https://arxiv.org/abs/2112.00845.
23. An adaptive federated learning scheme with differential privacy preserving10.1016/j.future.2021.09.015 ↗
24. A comprehensive survey on local differential privacy
25. S. dano and T. Murakami, “Degree-preserving randomized response for graph neural networks under local differential privacy,” arXiv: 2202.10209, 2022. [Online]. Available: https://arxiv.org/abs/2202.10209.
26. Privacy-preserving data splitting: A combinatorial approach10.1007/s10623-021-00884-6 ↗
27. Rings for privacy: An architecture for large scale privacy-preserving data mining10.1109/TPDS.2021.3049286 ↗
28. An efficient high-dimensional data releasing method with differential privacy protection10.1109/ACCESS.2019.2957858 ↗
29. T. Su, H. Qi and M. Brown, “Measuring the effects of non-identical data distribution for federated visual classification,” arXiv: 1909.06335, 2019. [Online]. Available: https://arxiv.org/abs/1909.06335.
30. Y. Hao, M. Li and Lai, “Federated learning with Non-IID data,” arXiv: 1806.00582, 2022. [Online]. Available: https://arxiv.org/abs/1806.00582.
31. Approaches to address the data skew problem in federated learning