• Publications
  • Influence
FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
We introduce FedGraphNN, an open research federated learning system and a benchmark to facilitate GNN-based FL research. Expand
A highly efficient recurrent neural network architecture for data regression
In this paper, we study online nonlinear data regression and propose a highly efficient long short term memory (LSTM) network based architecture to reduce the total number of parameters to be learned. Expand
SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks
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.Expand