Federated Adaptation of Reservoirs via Intrinsic Plasticity
This work addresses federated learning challenges for Echo State Networks in client-server scenarios, offering an incremental improvement over existing methods.
The paper tackled the problem of federated learning with Echo State Networks by proposing an algorithm that combines Intrinsic Plasticity with Federated Averaging to adapt reservoirs, resulting in a significant improvement in the global model's performance on real-world human monitoring datasets.
We propose a novel algorithm for performing federated learning with Echo State Networks (ESNs) in a client-server scenario. In particular, our proposal focuses on the adaptation of reservoirs by combining Intrinsic Plasticity with Federated Averaging. The former is a gradient-based method for adapting the reservoir's non-linearity in a local and unsupervised manner, while the latter provides the framework for learning in the federated scenario. We evaluate our approach on real-world datasets from human monitoring, in comparison with the previous approach for federated ESNs existing in literature. Results show that adapting the reservoir with our algorithm provides a significant improvement on the performance of the global model.