Feature-Based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy
In this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing approaches in federated learning and federated transfer learning. Specifically, in t...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Transactions on Machine Learning in Communications and Networking |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10542971/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850226936677138432 |
|---|---|
| author | Feng Wang M. Cenk Gursoy Senem Velipasalar |
| author_facet | Feng Wang M. Cenk Gursoy Senem Velipasalar |
| author_sort | Feng Wang |
| collection | DOAJ |
| description | In this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing approaches in federated learning and federated transfer learning. Specifically, in the proposed feature-based federated learning, we design the extracted features and outputs to be uploaded instead of parameter updates. For this distributed learning model, we determine the required payload and provide comparisons with the existing schemes. Subsequently, we analyze the robustness of feature-based federated transfer learning against packet loss, data insufficiency, and quantization. Finally, we address privacy considerations by defining and analyzing label privacy leakage and feature privacy leakage, and investigating mitigating approaches. For all aforementioned analyses, we evaluate the performance of the proposed learning scheme via experiments on an image classification task and a natural language processing task to demonstrate its effectiveness (<uri>https://github.com/wfwf10/Feature-based-Federated-Transfer-Learning</uri>). |
| format | Article |
| id | doaj-art-c40c1c718eac4355b17872a5c74ff4de |
| institution | OA Journals |
| issn | 2831-316X |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Machine Learning in Communications and Networking |
| spelling | doaj-art-c40c1c718eac4355b17872a5c74ff4de2025-08-20T02:04:58ZengIEEEIEEE Transactions on Machine Learning in Communications and Networking2831-316X2024-01-01282384010.1109/TMLCN.2024.340813110542971Feature-Based Federated Transfer Learning: Communication Efficiency, Robustness and PrivacyFeng Wang0https://orcid.org/0000-0001-8071-9995M. Cenk Gursoy1https://orcid.org/0000-0002-7352-1013Senem Velipasalar2https://orcid.org/0000-0002-1430-1555Department of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USADepartment of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USADepartment of Electrical Engineering and Computer Science, Syracuse University, Syracuse, NY, USAIn this paper, we propose feature-based federated transfer learning as a novel approach to improve communication efficiency by reducing the uplink payload by multiple orders of magnitude compared to that of existing approaches in federated learning and federated transfer learning. Specifically, in the proposed feature-based federated learning, we design the extracted features and outputs to be uploaded instead of parameter updates. For this distributed learning model, we determine the required payload and provide comparisons with the existing schemes. Subsequently, we analyze the robustness of feature-based federated transfer learning against packet loss, data insufficiency, and quantization. Finally, we address privacy considerations by defining and analyzing label privacy leakage and feature privacy leakage, and investigating mitigating approaches. For all aforementioned analyses, we evaluate the performance of the proposed learning scheme via experiments on an image classification task and a natural language processing task to demonstrate its effectiveness (<uri>https://github.com/wfwf10/Feature-based-Federated-Transfer-Learning</uri>).https://ieeexplore.ieee.org/document/10542971/Federated learningtransfer learningcommunication efficiencyrobustnessprivacy |
| spellingShingle | Feng Wang M. Cenk Gursoy Senem Velipasalar Feature-Based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy IEEE Transactions on Machine Learning in Communications and Networking Federated learning transfer learning communication efficiency robustness privacy |
| title | Feature-Based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy |
| title_full | Feature-Based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy |
| title_fullStr | Feature-Based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy |
| title_full_unstemmed | Feature-Based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy |
| title_short | Feature-Based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy |
| title_sort | feature based federated transfer learning communication efficiency robustness and privacy |
| topic | Federated learning transfer learning communication efficiency robustness privacy |
| url | https://ieeexplore.ieee.org/document/10542971/ |
| work_keys_str_mv | AT fengwang featurebasedfederatedtransferlearningcommunicationefficiencyrobustnessandprivacy AT mcenkgursoy featurebasedfederatedtransferlearningcommunicationefficiencyrobustnessandprivacy AT senemvelipasalar featurebasedfederatedtransferlearningcommunicationefficiencyrobustnessandprivacy |