Conference paper Open Access

Federated Reservoir Computing Neural Networks

Bacciu, Davide; Di Sarli, Daniele; Faraji, Pouria; Gallicchio, Claudio; Micheli, Alessio

A critical aspect in Federated Learning is the aggregation strategy for the combination of multiple models, trained on the edge, into a single model that incorporates all the knowledge in the federation. Common Federated Learning approaches for Recurrent Neural Networks (RNNs) do not provide guarantees on the predictive performance of the aggregated model. In this paper we show how the use of Echo State Networks (ESNs), which are efficient state-of-the-art RNN models for time-series processing, enables a form of federation that is optimal in the sense that it produces models mathematically equivalent to the corresponding centralized model. Furthermore, the proposed method is compliant with privacy constraints.
The proposed method, which we denote as Incremental Federated Learning, is experimentally evaluated against an averaging strategy on two datasets for human state and activity recognition.

Files (223.4 kB)
Name Size
Incremental_Federated_Learning__Zenodo_.pdf
md5:a45073f203ce93fa1047d47766be0c61
223.4 kB Download
25
31
views
downloads
All versions This version
Views 2525
Downloads 3131
Data volume 6.9 MB6.9 MB
Unique views 2121
Unique downloads 2828

Share

Cite as