Personalized Federated Learning With Differential Privacy

By Rui Hu, Yuanxiong Guo, Hongning Li, Qingqi Pei, Yanmin Gong. IEEE Internet of Things Journal, 2020

325 citations recorded by the source corpus.

To provide intelligent and personalized services on smart devices, machine learning techniques have been widely used to learn from data, identify patterns, and make automated decisions. Machine learning processes typically require a large amount of representative data that are often collected through crowdsourcing from end users. However, user data could be sensitive in nature, and training machine learning models on these data may expose sensitive information of users, violating their privacy. Moreover, to meet the increasing demand of personalized services, these learned models should capture their individual characteristics. This article proposes a privacy-preserving approach for learning effective personalized models on distributed user data while guaranteeing the differential privacy of user data. Practical issues in a distributed learning system such as user heterogeneity are considered in the proposed approach. In addition, the convergence property and privacy guarantee of the proposed approach are rigorously analyzed. The experimental results on realistic mobile sensing data demonstrate that the proposed approach is robust to user heterogeneity and offers a good tradeoff between accuracy and privacy.

Subfields: Artificial Intelligence, Computer Science Applications, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/06331192794ca97dfe7826e50571a2835677f13b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bo Du
2. Mang Ye
3. Pong Chi Yuen
4. Dinh C. Nguyen
5. Pubudu N. Pathirana
6. Ming Ding
7. Lingjuan Lyu
8. Aruna Prasad Seneviratne

In Computer Science Applications

1. Jun Zhao
2. Dacheng Tao
3. Bo Du
4. Dusist Niyato
5. Jiankun Hu
6. Teng Wang
7. Yanming Zhu
8. Mang Ye

In Sociology and Political Science

1. Jun Zhao
2. Dacheng Tao
3. Nicholas Donald Lane
4. Ming Ding
5. Bo Du
6. Dusist Niyato
7. Jiankun Hu
8. Yanming Zhu

Citations in the corpus

• A Comprehensive Survey of Privacy-preserving Federated Learning (2021, methodology): “In some methods [52, 78, 193], random noise was added to weight updates to achieve privacy-preserving in the training process, whereas in other methods [69, 70, 172, 198], random noise was added to the gradient updates.”
• Federated Learning for Internet of Things: A Comprehensive Survey (2021, methodology): “As an example, differential privacy is applied in [189] by inserting artificial noise (e.”
• FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout (2021, background): “Until now, a lot of research effort has been invested with the sole goal of maximising the accuracy of the global model [49, 45, 42, 34, 66], while complementary mechanisms have been proposed to ensure privacy and robustness [7, 17, 50, 51, 30, 5].”
• Local Differential Privacy-Based Federated Learning for Internet of Things (2020, background): “[37] propose a privacy-preserving FL approach for learning effective personalized models.”
• Heterogeneous Federated Learning: State-of-the-art and Research Challenges (2023, methodology): “[80] propose a federated learning method for personalized local DP, PLDP-PFL.”