Global Group Fairness in Federated Learning via Function Tracking
This work addresses fairness in distributed machine learning for applications like healthcare or finance, though it is incremental as it builds on existing federated learning and fairness methods.
The paper tackles the challenge of ensuring global group fairness in federated learning by introducing a function-tracking scheme based on Maximum Mean Discrepancy (MMD) to handle non-separable fairness regularizers across distributed clients, achieving this with small communication overhead and integration into algorithms like FedAvg while maintaining convergence guarantees.
We investigate group fairness regularizers in federated learning, aiming to train a globally fair model in a distributed setting. Ensuring global fairness in distributed training presents unique challenges, as fairness regularizers typically involve probability metrics between distributions across all clients and are not naturally separable by client. To address this, we introduce a function-tracking scheme for the global fairness regularizer based on a Maximum Mean Discrepancy (MMD), which incurs a small communication overhead. This scheme seamlessly integrates into most federated learning algorithms while preserving rigorous convergence guarantees, as demonstrated in the context of FedAvg. Additionally, when enforcing differential privacy, the kernel-based MMD regularization enables straightforward analysis through a change of kernel, leveraging an intuitive interpretation of kernel convolution. Numerical experiments confirm our theoretical insights.