Reprint

Federated and Transfer Learning Applications

Edited by
April 2024
212 pages
  • ISBN978-3-7258-0075-9 (Hardback)
  • ISBN978-3-7258-0076-6 (PDF)

This is a Reprint of the Special Issue Federated and Transfer Learning Applications that was published in

Biology & Life Sciences
Chemistry & Materials Science
Computer Science & Mathematics
Engineering
Environmental & Earth Sciences
Physical Sciences
Summary

The classic example of machine learning is based on isolated learning—a single model for each task using a single dataset. Most deep learning methods require a significant amount of labeled data, preventing their applicability in many areas where there is a shortage. In these cases, the ability of models to leverage information from unlabeled data or data that are not publicly available (for privacy and security reasons) can offer a remarkable alternative. Transfer learning and federated learning are alternative approaches that have emerged in recent years. More precisely, transfer learning is defined as the set of methods that leverage data from additional fields or tasks to train a model with greater generalizability and usually use a smaller amount of labeled data (via fine-tuning) to make them more specific for dedicated tasks. Accordingly, federated learning is a learning model that seeks to address the problem of data management and privacy through joint training with these data without the need to transfer the data to a central entity. With this in mind, this Special Issue of Applied Sciences provides an overview of the latest developments in this field.

Format
  • Hardback
License and Copyright
© 2022 by the authors; CC BY-NC-ND license
Keywords
federated learning; heterogeneous data; lazy aggregation; cross-device momentum; survey; federated learning; deep learning; machine learning; distributed learning; privacy; security; blockchain; deep learning security and privacy threats; federated learning; heterogeneity; non-IID; regularization; layer-wise similarity; classification; convolutional neural network; recurrent neural networks; MNIST; model selection; federated learning; framework; cluster analysis; cluster number determination; federated fuzzy Davies–Bouldin index; federated cluster validation metric; federated fuzzy c-means; Drug–Drug Interactions; transformers; graph neural networks; language models; relation classification; domain-adaption; private 5G networks; anomaly detection; abnormal early warning; autoencoder; long short-term memory; transfer learning; decentralized federated learning; blockchain; edge computing; stable matching; consensus algorithm; federated learning (FL); federated averaging (FedAvg); federated SGD (FedSGD); unreliable participants; selective aggregation; wireless traffic prediction; federal learning; FedAvg; deep learning; gradient similarity; social engineering; dialogue-state tracking; chatbot; n/a

Related Books

October 2023

Deep Learning Architecture and Applications

Computer Science & Mathematics
August 2022

Computational Methods for Medical and Cyber Security

Computer Science & Mathematics
August 2023

Advanced Machine Learning Applications in Big Data Analytics

Social Sciences, Arts & Humanities
...