64 citations · 140 across the 18 of their papers we have counts for
5 papers · 1 filter
Towards Sparsified Federated Neuroimaging Models via Weight Pruning
Dimitris Stripelis, Umang Gupta, Nikhil Dhinagar +3
Federated training of large deep neural networks can often be restrictive due to the increasing costs of communicating the updates with increasing model sizes. Various model prunin…
Performance Weighting for Robust Federated Learning Against Corrupted Sources
Dimitris Stripelis, Marcin Abram, Jose Luis Ambite
Federated Learning has emerged as a dominant computational paradigm for distributed machine learning. Its unique data privacy properties allow us to collaboratively train models wh…
Secure & Private Federated Neuroimaging
Dimitris Stripelis, Umang Gupta, Hamza Saleem +9
The amount of biomedical data continues to grow rapidly. However, collecting data from multiple sites for joint analysis remains challenging due to security, privacy, and regulator…
Federated Progressive Sparsification (Purge, Merge, Tune)+
Dimitris Stripelis, Umang Gupta, Greg Ver Steeg +1
To improve federated training of neural networks, we develop FedSparsify, a sparsification strategy based on progressive weight magnitude pruning. Our method has several benefits.…
Federated Named Entity Recognition
Joel Mathew, Dimitris Stripelis, José Luis Ambite
We present an analysis of the performance of Federated Learning in a paradigmatic natural-language processing task: Named-Entity Recognition (NER). For our evaluation, we use the l…