Search Results for author:
Found 3 papers, 0 papers with code
Knowledge Enhanced Graph Neural Networks for Graph Completion
On one hand, neural methods, such as graph neural networks, have proven to be robust tools for learning rich representations of noisy graphs.
Constrained Differentially Private Federated Learning for Low-bandwidth Devices
This bandwidth and corresponding processing costs could be prohibitive if the participating entities are, for example, mobile devices.
Compression Boosts Differentially Private Federated Learning
In this paper, compressive sensing is used to reduce the model size and hence increase model quality without sacrificing privacy.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
