Emir Ceyani

University of Southern California
0000-0002-4107-1337
https://ceyani.io/
Publications5
h-index2
Citations60
Highly Influential Citations7
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • Chaoyang He
  • 33 Publications • 2,336 Citations
  • H. B. McMahan
  • 77 Publications • 21,563 Citations
  • Virginia Smith
  • 51 Publications • 5,486 Citations
  • Carl Yang
  • 98 Publications • 1,559 Citations
  • Publications
  • Influence
FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
TLDR
FedGraphNN is an open research federated learning system and a benchmark to facilitate GNN-based FL research, built on a unified formulation of federated GNNs and supports commonly used datasets, GNN models, FL algorithms, and flexible APIs.
View PDF on arXiv
SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks
TLDR
SpreadGNN is proposed, a novel multi-task federated training framework capable of operating in the presence of partial labels and absence of a central server for the first time in the literature, and demonstrates the efficacy of the framework on a variety of non-I.I.D. distributed graph-level molecular property prediction datasets with partial labels.
View PDF on arXiv
A highly efficient recurrent neural network architecture for data regression
TLDR
This paper proposes a highly efficient long short term memory (LSTM) network based architecture for data regression and introduces online learning methods based on the exponentiated gradient (EG) and stochastic gradient descent (SGD) algorithms.
View on IEEE
SpreadGNN: Decentralized Multi-Task Federated Learning for Graph Neural Networks on Molecular Data
Graph Neural Networks (GNNs) are the first choice methods for graph machine learning problems thanks to their ability to learn state-of-the-art level representations from graph-structured data.…
View via Publisher
Federated Learning of Generative Image Priors for MRI Reconstruction
TLDR
Detailed experiments on multi-institutional datasets clearly demonstrate enhanced generalization performance of FedGIMP against site-specific and federated methods based on conditional models, as well as traditional reconstruction methods.
View PDF on arXiv