Disha Makhija

federated learning (2) differential privacy (1) representation learning (1) semi-supervised learning (1) label propagation (1) model aggregation (1) community detection (1) graph-based learning (1) stochastic block model (1) personalized model (1) privacy auditing (1) bayesian neural network (1) hidden state analysis (1) membership inference attack (1) personalized learning (1) attention pattern (1) heterogeneous architecture (1) neural network (1) heterogeneous setting (1) training data exposure (1)