Personalised federated learning with differential privacy and gradient selection
The fast-emerging field of federated learning holds the promise of allowing clients to contribute to a central machine learning model without the need to send their data to a central server, thus providing privacy for their data. Two issues arise: dealing with statistical heterogeneity in datasets,...
Saved in:
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/151517 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | The fast-emerging field of federated learning holds the promise of allowing clients to contribute to a central machine learning model without the need to send their data to a central server, thus providing privacy for their data. Two issues arise: dealing with statistical heterogeneity in datasets, which is often the case in real-world settings, and obtaining stricter data privacy through employing privacy-preserving mechanisms. In this paper, we use personalized layers in a federated Convolutional Neural Network model to address statistical heterogeneity and use differential privacy to provide mathematically rigorous privacy guarantees for the federated learning model. We also propose a gradient selection technique to increase model performance. We developed a framework combining these techniques and experimentally demonstrate the effectiveness of the proposed framework on a dataset in improving model performance whilst maintaining a reasonable level of privacy guarantee and training efficiency. |
|---|