Privacy-Preserving and Robust Machine Learning at the Edge

Proposed the first approach to enable privacy-preserving classification in hyperbolic geometry in the federated setting.

Proposed the first known unlearning mechanism for federated clustering with privacy criteria that support simple, provable, and efficient data removal at the client and server level.

Presented methodologies for sparse federated learning for resource constrained edge (both homogeneous and heterogeneous compute budget).

Provided a sub-model training method that enabled resource-constrained clients to train large models in federated learning settings.

Proposed a novel sampling based approach that applies per client criteria for mitigating faults in the general federated learning setting.

Developed a fast and computationally efficient Byzantine robust algorithm that leverages a sequential, memory assisted and performance criteria for training over a logical ring.

Proposed CodedFedL that injects structured coding redundancy into non-linear federated learning for mitigating stragglers and speeding up training procedure in heterogeneous MEC networks.

Formulated a problem for decentralized training from data at the edge users, incorporating the challenges of straggling communications and limited communication bandwidth.