FedNolowe: A Normalized Loss-Based Weighted Aggregation Strategy for Robust Federated Learning in Heterogeneous Environments
Le, D.-D.; Huynh, T.-N.; Tran, A.-K.; Dao, M.-S.; Bao, P. T.
Show abstract
Federated Learning supports collaborative model training across distributed clients while keeping sensitive data decentralized. Still, non-independent and identically distributed data pose challenges like unstable convergence and client drift. We propose Federated Normalized Loss-based Weighted Aggregation (FedNolowe), a new method that weights client contributions using normalized training losses, favoring those with lower losses to improve global model stability. Unlike prior methods tied to dataset sizes or resource-heavy techniques, FedNolowe employs a two-stage Manhattan normalization, reducing computational complexity by 40% in floating-point operations while matching state-of-the-art performance. A detailed sensitivity analysis shows our two-stage weighting maintains stability in heterogeneous settings by mitigating extreme loss impacts while remaining effective in independent and identically distributed scenarios.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare 94%
- Sparse Epistatic Regularization of Deep Neural Networks for Inferring Fitness Functions 93%
- An adaptive weight ensemble approach to forecast influenza activity in the context of irregular seasonality 92%
Similar papers in this journal
- A novel interpretable deep transfer learning combining diverse learnable parameters for improved T2D prediction based on single-cell gene regulatory networks 94%
- An Assistive Computer Vision Tool to Automatically Detect Changes in Fish Behavior In Response to Ambient Odor 93%
- WormSwin: Instance segmentation of C. elegans using vision transformer 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.