On Homomorphic Encryption Based Strategies for Class Imbalance in Federated Learning
This addresses bias and poor generalization in federated learning for distributed environments, though it is incremental as it applies existing encryption to a known bottleneck.
The paper tackles global class imbalance in federated learning by proposing FLICKER, a privacy-preserving framework using homomorphic encryption to balance datasets, which significantly improves accuracy in experiments.
Class imbalance in training datasets can lead to bias and poor generalization in machine learning models. While pre-processing of training datasets can efficiently address both these issues in centralized learning environments, it is challenging to detect and address these issues in a distributed learning environment such as federated learning. In this paper, we propose FLICKER, a privacy preserving framework to address issues related to global class imbalance in federated learning. At the heart of our contribution lies the popular CKKS homomorphic encryption scheme, which is used by the clients to privately share their data attributes, and subsequently balance their datasets before implementing the FL scheme. Extensive experimental results show that our proposed method significantly improves the FL accuracy numbers when used along with popular datasets and relevant baselines.