Research map / Federated learning and privacy / Personalized and heterogeneous FL
RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility
Dawood Wasif, Terrence J Moore, Jin-Hee Cho
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use RESFL (adversarial disentanglement + UFM-weighted aggregation) instead of FedAvg | federated YOLOv8 · FACET | Delta EOP: 0.2362 -> 0.1959 | Improved |
| use RESFL instead of FedAvg | federated YOLOv8 · FACET | MIA / AIA success rate: MIA 0.3341 -> 0.2093; AIA 0.4431 -> 0.1832 | Improved |
| use RESFL instead of FedAvg | federated YOLOv8 · FACET | mAP: 0.6378 -> 0.6654 | Improved |
| use RESFL instead of FedAvg | federated YOLOv8 · FACET | |1-DI|: 0.2159 -> 0.2287 | Hurt |
| use RESFL instead of FairFed | federated YOLOv8 · FACET | mAP: 0.7013 -> 0.6654 | Hurt |
| add differential privacy (eps=1) to FedAvg | FedAvg · FACET | mAP: 0.6378 -> 0.4612 | Hurt |
| raise lambda_priv from 0.01 to 0.1 (lambda_fair=0.1) (ablation) | RESFL · FACET | mAP / Delta EOP: mAP 0.6654 -> 0.6430; Delta EOP 0.1959 -> 0.3143 | Hurt |
| raise lambda_priv from 0.01 to 1 (lambda_fair=0.1) (ablation) | RESFL · FACET | mAP / Delta EOP: mAP 0.6654 -> 0.5839; Delta EOP 0.1959 -> 0.4146 | Hurt |
| raise lambda_priv from 0.01 to 0.1 (lambda_fair=0.1) (ablation) | RESFL · FACET | MIA success rate: 0.2093 -> 0.1363 | Improved |
| raise lambda_fair from 0.01 to 1 (lambda_priv=1) (ablation) | RESFL · FACET | Delta EOP: 0.3459 -> 0.2513 | Improved |
| raise lambda_fair from 0.01 to 1 (lambda_priv=1) (ablation) | RESFL · FACET | mAP: 0.6056 -> 0.5953 (peak 0.6254 at 0.1) | Mixed |
| use RESFL on CARLA under 100% fog vs other FL methods | RESFL (fine-tuned) · CARLA fog 100% | mAP: 0.17 vs others <0.10 | Improved |
Closest papers by meaning
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.85)
- FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning (AAAI 2025 · similarity 0.85)
- Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning (ICML 2024 · similarity 0.85)
- Towards Trustworthy Federated Learning with Untrusted Participants (ICML 2025 · similarity 0.85)
- Towards the Robustness of Differentially Private Federated Learning (AAAI 2024 · similarity 0.84)
- A New Federated Learning Framework Against Gradient Inversion Attacks (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
