Predicting Infant Brain Connectivity with Federated Multi-Trajectory GNNs using Scarce Data

1 code implementation • 1 Jan 2024 • Michalis Pistos, Gang Li, Weili Lin, Dinggang Shen, Islem Rekik

The three key innovations of FedGmTE-Net++ are: (i) presenting the first federated learning framework specifically designed for brain multi-trajectory evolution prediction in a data-scarce environment, (ii) incorporating an auxiliary regularizer in the local objective function to exploit all the longitudinal brain connectivity within the evolution trajectory and maximize data utilization, (iii) introducing a two-step imputation process, comprising a preliminary KNN-based precompletion followed by an imputation refinement step that employs regressors to improve similarity scores and refine imputations.

Federated Learning Imputation +1