Communication-Efficient and Privacy-Preserving Feature-based Federated Transfer Learning
This addresses communication bottlenecks for privacy-preserving federated learning systems, particularly in bandwidth-limited scenarios, though it appears incremental as an optimization of existing federated transfer learning frameworks.
The paper tackles the communication inefficiency in federated transfer learning over wireless links by proposing a feature-based approach that reduces uplink payload by over five orders of magnitude compared to existing methods, as demonstrated on an image classification task.
Federated learning has attracted growing interest as it preserves the clients' privacy. As a variant of federated learning, federated transfer learning utilizes the knowledge from similar tasks and thus has also been intensively studied. However, due to the limited radio spectrum, the communication efficiency of federated learning via wireless links is critical since some tasks may require thousands of Terabytes of uplink payload. In order to improve the communication efficiency, we in this paper propose the feature-based federated transfer learning as an innovative approach to reduce the uplink payload by more than five orders of magnitude compared to that of existing approaches. We first introduce the system design in which the extracted features and outputs are uploaded instead of parameter updates, and then determine the required payload with this approach and provide comparisons with the existing approaches. Subsequently, we analyze the random shuffling scheme that preserves the clients' privacy. Finally, we evaluate the performance of the proposed learning scheme via experiments on an image classification task to show its effectiveness.