STFL: A Temporal-Spatial Federated Learning Framework for Graph Neural Networks
This work addresses data privacy and generalization challenges in graph prediction tasks for domains like healthcare, but it appears incremental as it combines existing federated learning and graph neural network concepts.
The authors tackled the problem of learning from spatial-temporal data in a privacy-preserving manner by proposing STFL, a federated learning framework for graph neural networks that transforms input data into node features and adjacency matrices, achieving effective model generalization on the ISRUC_S3 sleep stage dataset.
We present a spatial-temporal federated learning framework for graph neural networks, namely STFL. The framework explores the underlying correlation of the input spatial-temporal data and transform it to both node features and adjacency matrix. The federated learning setting in the framework ensures data privacy while achieving a good model generalization. Experiments results on the sleep stage dataset, ISRUC_S3, illustrate the effectiveness of STFL on graph prediction tasks.