Search Results for author: Jose Luis Ambite

Found 10 papers, 0 papers with code

Secure Federated Learning for Neuroimaging

no code implementations11 May 2022 Dimitris Stripelis, Umang Gupta, Hamza Saleem, Nikhil Dhinagar, Tanmay Ghai, Rafael Sanchez, Chrysovalantis Anastasiou, Armaghan Asghar, Greg Ver Steeg, Srivatsan Ravi, Muhammad Naveed, Paul M. Thompson, Jose Luis Ambite

Specifically, we investigate training neural models to classify Alzheimer's disease, and estimate Brain Age, from magnetic resonance imaging datasets distributed across multiple sites, including heterogeneous environments where sites have different amounts of data, statistical distributions, and computational capabilities.

Federated Learning

Performance Weighting for Robust Federated Learning Against Corrupted Sources

no code implementations2 May 2022 Dimitris Stripelis, Marcin Abram, Jose Luis Ambite

Here, we focus on the latter, the susceptibility of federated learning to various data corruption attacks.

Federated Learning

Federated Progressive Sparsification (Purge, Merge, Tune)+

no code implementations26 Apr 2022 Dimitris Stripelis, Umang Gupta, Greg Ver Steeg, Jose Luis Ambite

Second, the models are incrementally constrained to a smaller set of parameters, which facilitates alignment/merging of the local models and improved learning performance at high sparsification rates.

Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryption

no code implementations7 Aug 2021 Dimitris Stripelis, Hamza Saleem, Tanmay Ghai, Nikhil Dhinagar, Umang Gupta, Chrysovalantis Anastasiou, Greg Ver Steeg, Srivatsan Ravi, Muhammad Naveed, Paul M. Thompson, Jose Luis Ambite

Federated learning (FL) enables distributed computation of machine learning models over various disparate, remote data sources, without requiring to transfer any individual data to a centralized location.

Federated Learning

Semi-Synchronous Federated Learning

no code implementations4 Feb 2021 Dimitris Stripelis, Jose Luis Ambite

There are situations where data relevant to a machine learning problem are distributed among multiple locations that cannot share the data due to regulatory, competitiveness, or privacy reasons.

Federated Learning

Accelerating Federated Learning in Heterogeneous Data and Computational Environments

no code implementations25 Aug 2020 Dimitris Stripelis, Jose Luis Ambite

There are situations where data relevant to a machine learning problem are distributed among multiple locations that cannot share the data due to regulatory, competitiveness, or privacy reasons.

Federated Learning

NSEEN: Neural Semantic Embedding for Entity Normalization

no code implementations19 Nov 2018 Shobeir Fakhraei, Joel Mathew, Jose Luis Ambite

An important task in this process is entity normalization, which consists of mapping noisy entity mentions in text to canonical entities in well-known reference sets.

Entity Resolution Knowledge Graphs

Learning the Semantics of Structured Data Sources

no code implementations16 Jan 2016 Mohsen Taheriyan, Craig A. Knoblock, Pedro Szekely, Jose Luis Ambite

This model represents the semantics of the new source in terms of the concepts and relationships defined by the domain ontology.

Knowledge Graphs

Cannot find the paper you are looking for? You can Submit a new open access paper.