Federated Time Series Classification with ROCKET features
This paper proposes FROCKS, a federated time series classification method using ROCKET features. Our approach dynamically adapts the models features by selecting and exchanging the best-performing ROCKET kernels from a federation of clients. Specifically, the server gathers the best-performing kernels of the clients together with the associated model parameters, and it performs a weighted average if a kernel is best-performing for more than one client. We compare the proposed method with state-of-the-art approaches on the UCR archive binary classification datasets and show superior performance on most datasets.
- Published in:
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Type:
Inproceedings - Authors:
Casella, Bruno; Jakobs, Matthias; Aldinucci, Marco; Buschjäger, Sebastian - Year:
2024
Citation information
Casella, Bruno; Jakobs, Matthias; Aldinucci, Marco; Buschjäger, Sebastian: Federated Time Series Classification with ROCKET features, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2024, https://iris.unito.it/handle/2318/2012811, Casella.etal.2024a,
@Inproceedings{Casella.etal.2024a,
author={Casella, Bruno; Jakobs, Matthias; Aldinucci, Marco; Buschjäger, Sebastian},
title={Federated Time Series Classification with ROCKET features},
booktitle={European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning},
url={https://iris.unito.it/handle/2318/2012811},
year={2024},
abstract={This paper proposes FROCKS, a federated time series classification method using ROCKET features. Our approach dynamically adapts the models features by selecting and exchanging the best-performing ROCKET kernels from a federation of clients. Specifically, the server gathers the best-performing kernels of the clients together with the associated model parameters, and it performs a weighted average...}}
