Different Corruptions, Different Signals: Uncertainty and Loss in Federated Data Quality
cs.LG, cs.AI, cs.CV
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/bs97/different-corruptions-different-signals
Terminology
Sources
- SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection
- FNBench: Benchmarking Robust Federated Learning against Noisy Labels
- Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization
- Bayesian Active Learning for Classification and Preference Learning
- Flower: A Friendly Federated Learning Research Framework
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks