global model
A model that is trained on data from various sources or locations, aiming for a comprehensive understanding across diverse scenarios. Global models can enhance robustness and applicability but may face challenges related to data heterogeneity.
- DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
- FedIGL: Federated Invariant Graph Learning for Non-IID Graphs
- FedLPA: Local Prior Alignment for Heterogeneous Federated Generalized Category Discovery
- Rising from Ashes: Generalized Federated Learning via Dynamic Parameter Reset
- Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning