Towards Causal Federated Learning For Enhanced Robustness and Privacy
This addresses robustness and privacy issues in federated learning for distributed machine learning applications, representing an incremental improvement.
The paper tackles the challenges of non-i.i.d. data and security vulnerabilities in federated learning by proposing an approach to learn invariant causal features across clients, which empirically enhances out-of-distribution accuracy and privacy in the final model.
Federated Learning is an emerging privacy-preserving distributed machine learning approach to building a shared model by performing distributed training locally on participating devices (clients) and aggregating the local models into a global one. As this approach prevents data collection and aggregation, it helps in reducing associated privacy risks to a great extent. However, the data samples across all participating clients are usually not independent and identically distributed (non-iid), and Out of Distribution(OOD) generalization for the learned models can be poor. Besides this challenge, federated learning also remains vulnerable to various attacks on security wherein a few malicious participating entities work towards inserting backdoors, degrading the generated aggregated model as well as inferring the data owned by participating entities. In this paper, we propose an approach for learning invariant (causal) features common to all participating clients in a federated learning setup and analyze empirically how it enhances the Out of Distribution (OOD) accuracy as well as the privacy of the final learned model.