Resumen
In recent years federated learning has emerged as a new paradigm for training machine learning models oriented to distributed systems. The main idea is that each node of a distributed system independently trains a model and shares only model parameters, such as weights, and does not share the training data set, which favors aspects such as security and privacy. Subsequently, and in a centralized way, a collective model is built that gathers all the information provided by all of the participating nodes. Several federated learning framework proposals have been developed that seek to optimize any aspect of the learning process. However, a lack of flexibility and dynamism is evident in many cases. In this regard, this study aims to provide flexibility and dynamism to the federated learning process. The methodology used consists of designing a multi-agent system that can form a federated learning framework where the agents act as nodes that can be easily added to the system dynamically. The proposal has been evaluated with different experiments on the SPADE platform; the results obtained demonstrate the benefits of the federated system while facilitating flexibility and scalability.