Federated Pruning: Improving Neural Network Efficiency with Federated Learning
This work addresses privacy and resource constraints in federated learning for speech recognition, but it is incremental as it applies existing pruning techniques to a federated context.
The paper tackles the challenge of training large automatic speech recognition models in federated learning settings with limited client resources by proposing Federated Pruning, which reduces model size while maintaining similar performance to full models and leveraging client data to improve pruning results.
Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns. Federated learning has been widely used and is considered to be an effective decentralized technique by collaboratively learning a shared prediction model while keeping the data local on different clients devices. However, the limited computation and communication resources on clients devices present practical difficulties for large models. To overcome such challenges, we propose Federated Pruning to train a reduced model under the federated setting, while maintaining similar performance compared to the full model. Moreover, the vast amount of clients data can also be leveraged to improve the pruning results compared to centralized training. We explore different pruning schemes and provide empirical evidence of the effectiveness of our methods.