Federated Learning for Time Series Forecasting Using LSTM Networks: Exploiting Similarities Through Clustering

Federated Learning for Time Series Forecasting Using LSTM Networks: Exploiting Similarities Through Clustering

Federated learning poses a statistical challenge when training on highly heterogeneous sequence data. For example, time-series telecom data collected over long intervals regularly shows mixed fluctuations and patterns. These distinct distributions are an inconvenience when a node not only plans to c...

Full description

Bibliographic Details
Main Author: Díaz González, Fernando
Format: Others
Language:English
Published: KTH, Skolan för elektroteknik och datavetenskap (EECS) 2019
Subjects:
Federated Learning
Time Series Forecasting
Clustering
Time Series Feature Extraction
Recurrent Neural Networks
Long Short-Term Memory
Computer and Information Sciences
Data- och informationsvetenskap
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254665

Internet

http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254665

Similar Items