Concept drift detection and adaptation for federated and continual learning
| Autor: | Fernando E. Casado, Marcos F. Criado, Roberto Iglesias, Senén Barro, Dylan Lema, Carlos V. Regueiro |
|---|---|
| Přispěvatelé: | Universidade de Santiago de Compostela. Centro de Investigación en Tecnoloxías da Información, Universidade de Santiago de Compostela. Departamento de Electrónica e Computación |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Information privacy Computer Science - Machine Learning Concept drift Computer Networks and Communications Computer science Federated learning Wearable computer Catastrophic forgetting 02 engineering and technology Field (computer science) Machine Learning (cs.LG) User experience design 020204 information systems 0202 electrical engineering electronic engineering information engineering Media Technology Nonstationarity Adaptation (computer science) business.industry Deep learning Federated Averaging Data science Hardware and Architecture Rehearsal Robot 020201 artificial intelligence & image processing Artificial intelligence Continual learning business Software |
| Zdroj: | Minerva: Repositorio Institucional de la Universidad de Santiago de Compostela Universidad de Santiago de Compostela (USC) RUC. Repositorio da Universidade da Coruña instname Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela |
| Popis: | [Abstract] Smart devices, such as smartphones, wearables, robots, and others, can collect vast amounts of data from their environment. This data is suitable for training machine learning models, which can significantly improve their behavior, and therefore, the user experience. Federated learning is a young and popular framework that allows multiple distributed devices to train deep learning models collaboratively while preserving data privacy. Nevertheless, this approach may not be optimal for scenarios where data distribution is non-identical among the participants or changes over time, causing what is known as concept drift. Little research has yet been done in this field, but this kind of situation is quite frequent in real life and poses new challenges to both continual and federated learning. Therefore, in this work, we present a new method, called Concept-Drift-Aware Federated Averaging (CDA-FedAvg). Our proposal is an extension of the most popular federated algorithm, Federated Averaging (FedAvg), enhancing it for continual adaptation under concept drift. We empirically demonstrate the weaknesses of regular FedAvg and prove that CDA-FedAvg outperforms it in this type of scenario. Xunta de Galicia; ED431G/01 Xunta de Galicia; ED431G/08 Xunta de Galicia; ED431C2018/29 Xunta de Galicia; ED431F2018/02 Esta investigación ha recibido apoyo financiero de la AEI/FEDER (UE) con número de subvención TIN2017-90135-R, así como de la Consellería de Cultura, Educación e Ordenación Universitaria de Galicia (acreditación 2016-2019, ED431G/01 y ED431G/08, grupo competitivo de referencia ED431C2018/29, y subvención ED431F2018/02), y del Fondo Europeo de Desarrollo Regional (FEDER). También ha sido apoyado por el Ministerio de Universidades de España en el programa FPU 2017 (FPU17/04154). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|