Privacy-preserving Transfer Learning via Secure Maximum Mean Discrepancy
This work addresses privacy concerns in federated learning for parties with isolated data, though it appears incremental as it adapts an existing method with encryption.
The paper tackles the problem of data isolation in machine learning by proposing a secure version of Maximum Mean Discrepancy (SMMD) using homomorphic encryption to enable privacy-preserving transfer learning in federated settings, preventing information leakage while allowing effective knowledge transfer.
The success of machine learning algorithms often relies on a large amount of high-quality data to train well-performed models. However, data is a valuable resource and are always held by different parties in reality. An effective solution to such a data isolation problem is to employ federated learning, which allows multiple parties to collaboratively train a model. In this paper, we propose a Secure version of the widely used Maximum Mean Discrepancy (SMMD) based on homomorphic encryption to enable effective knowledge transfer under the data federation setting without compromising the data privacy. The proposed SMMD is able to avoid the potential information leakage in transfer learning when aligning the source and target data distribution. As a result, both the source domain and target domain can fully utilize their data to build more scalable models. Experimental results demonstrate that our proposed SMMD is secure and effective.