Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selection
This addresses efficiency and privacy issues in federated learning for distributed machine learning applications, but it is incremental as it builds on existing cryptographic methods.
The paper tackles performance degradation in federated learning due to statistical heterogeneity by proposing Dubhe, a client selection method using homomorphic encryption, which achieves classification accuracy comparable to an optimal greedy method with minimal overhead.
Federated learning (FL) is a distributed machine learning paradigm that allows clients to collaboratively train a model over their own local data. FL promises the privacy of clients and its security can be strengthened by cryptographic methods such as additively homomorphic encryption (HE). However, the efficiency of FL could seriously suffer from the statistical heterogeneity in both the data distribution discrepancy among clients and the global distribution skewness. We mathematically demonstrate the cause of performance degradation in FL and examine the performance of FL over various datasets. To tackle the statistical heterogeneity problem, we propose a pluggable system-level client selection method named Dubhe, which allows clients to proactively participate in training, meanwhile preserving their privacy with the assistance of HE. Experimental results show that Dubhe is comparable with the optimal greedy method on the classification accuracy, with negligible encryption and communication overhead.