no code implementations • 24 Aug 2022 • Dimitris Stripelis, Umang Gupta, Nikhil Dhinagar, Greg Ver Steeg, Paul Thompson, José Luis Ambite
In our experiments in centralized and federated settings on the brain age prediction task (estimating a person's age from their brain MRI), we demonstrate that models can be pruned up to 95% sparsity without affecting performance even in challenging federated learning environments with highly heterogeneous data distributions.
no code implementations • 28 Mar 2022 • 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).
no code implementations • 10 Dec 2021 • Yijun Lin, Yao-Yi Chiang, Meredith Franklin, Sandrah P. Eckel, José Luis Ambite
In addition to a feature selection module and a spatiotemporal learning module, DeepLATTE contains an autocorrelation-guided semi-supervised learning strategy to enforce both local autocorrelation patterns and global autocorrelation trends of the predictions in the learned spatiotemporal embedding space to be consistent with the observed data, overcoming the limitation of sparse and unevenly distributed observations.
no code implementations • 6 May 2021 • Umang Gupta, Dimitris Stripelis, Pradeep K. Lam, Paul M. Thompson, José Luis Ambite, Greg Ver Steeg
In particular, we show that it is possible to infer if a sample was used to train the model given only access to the model prediction (black-box) or access to the model itself (white-box) and some leaked samples from the training data distribution.
no code implementations • 1 Jun 2019 • Joel Mathew, Shobeir Fakhraei, José Luis Ambite
Second, we use a reference set of entity names (e. g., proteins in UniProt) to identify entity mentions with high precision, but low recall, on an unlabeled corpus.