FedTLU: Federated Learning with Targeted Layer Updates
This addresses performance issues in federated learning for language models, but it is incremental as it builds on existing FL methods.
The paper tackled the problem of non-IID data harming convergence in federated fine-tuning of language models by proposing a targeted layer update strategy, which improved performance and efficiency in experiments.
Federated learning (FL) addresses privacy concerns in training language models by enabling multiple clients to contribute to the training, without sending their data to others. However, non-IID (identically and independently distributed) data across clients often limits FL's performance. This issue is especially challenging during model fine-tuning, as noise due to variations in clients' data distributions can harm model convergence near stationary points. This paper proposes a targeted layer update strategy for fine-tuning in FL. Instead of randomly updating layers of the language model, as often done in practice, we use a scoring mechanism to identify and update the most critical layers, avoiding excessively noisy or even poisoned updates by freezing the parameters in other layers. We show in extensive experiments that our method improves convergence and performance in non-IID settings, offering a more efficient approach to fine-tuning federated language models.