Context-aggregator: An approach of loss-and class imbalance-aware aggregation in federated learning
Federated Learning (FL) is an emerging distributed learning paradigm which offers data
privacy to contributing nodes in the collaborating environment. By exploiting the Individual …
privacy to contributing nodes in the collaborating environment. By exploiting the Individual …
Not all Minorities are Equal: Empty-Class-Aware Distillation for Heterogeneous Federated Learning
Data heterogeneity, characterized by disparities in local data distribution across clients,
poses a significant challenge in federated learning. Substantial efforts have been devoted to …
poses a significant challenge in federated learning. Substantial efforts have been devoted to …
A DQN-Based Multi-Objective Participant Selection for Efficient Federated Learning
T Xu, Y Liu, Z Ma, Y Huang, P Liu - Future Internet, 2023 - mdpi.com
As a new distributed machine learning (ML) approach, federated learning (FL) shows great
potential to preserve data privacy by enabling distributed data owners to collaboratively …
potential to preserve data privacy by enabling distributed data owners to collaboratively …
Federated learning on non-IID and long-tailed data via dual-decoupling
Z Wang, H Li, J Li, R Hu, B Wang - Frontiers of Information Technology & …, 2024 - Springer
Federated learning (FL), a cutting-edge distributed machine learning training paradigm,
aims to generate a global model by collaborating on the training of client models without …
aims to generate a global model by collaborating on the training of client models without …