Federated Probabilistic Representation Learning using Information Geometric Approach

Autonomous vehicles, IoT, and smart grids generate enormous amounts of edge data. Federated Learning (FL) enables privacy-preserving machine learning without transferring this edge data to a central server. Federated unsupervised learning is essential since labeling data at the edge is often impractical. We propose FLIP, a novel framework that uses information projection (I-projection) for probabilistic and federated representation learning. FLIP derives the global latent space distribution as the intersection of local distributions by applying the Pythagorean identity for I-projection. Clients update their local distribution parameters by minimizing reconstruction error on their data while incorporating the global distribution through I-projections expressed as KL divergence. Empirically, FLIP outperforms existing methods in federated unsupervised learning, showing robustness to data heterogeneity, variations in local epochs, and scalability across clients.