Dênis Rosário

A Distributed Aggregation Approach for Vehicular Federated Learning

2024 · IEEE Access

Federated Learning (FL) has rapidly become a crucial paradigm for training Machine Learning (ML) models when datasets are spread across several devices without compromising the privacy of the data owners. In vehicular networks, FL can …

ALFadapt: Mitigating Catastrophic Forgetting in Federated Learning

2025

Catastrophic forgetting, driven by concept drift, challenges federated learning (FL), especially in dynamic environments. Existing layer-freezing methods focus on communication efficiency but often overlook concept drift’s impact on individual neural network layers. We propose ALFadapt …