# Different Corruptions, Different Signals: Uncertainty and Loss in Federated Data Quality

arXiv: https://arxiv.org/abs/2609.31454 · HTML: https://mlsanity.com/paper/2609.31454/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasets](https://mlsanity.com/paper/2207.05471/) (2022)
- [Data Valuation and Detections in Federated Learning](https://mlsanity.com/paper/2311.05304/) (2023)
- [Federated Learning with Extremely Noisy Clients via Negative Distillation](https://mlsanity.com/paper/2312.12703/) (2023)
- [Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks](https://mlsanity.com/paper/2312.11230/) (2023)
- [FNBench: Benchmarking Robust Federated Learning against Noisy Labels](https://mlsanity.com/paper/2505.06684/) (2025)
- [Improving Label Error Detection and Elimination with Uncertainty Quantification](https://mlsanity.com/paper/2405.09602/) (2024)
- [SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection](https://mlsanity.com/paper/2308.02747/) (2023)
- [Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization](https://mlsanity.com/paper/2411.18385/) (2024)
- [Achieving Distributive Justice in Federated Learning via Uncertainty Quantification](https://mlsanity.com/paper/2504.15924/) (2025)
- [UDF-GMA: Uncertainty Disentanglement and Fusion for General Movement Assessment](https://mlsanity.com/paper/2507.04814/) (2025)

## Abstract (arXiv)

Federated learning (FL) data corruption can affect either inputs or labels, but it remains unclear whether input-conditional uncertainty and prediction-label loss expose these corruption modes equally. This paper compares two corruption-detection signals in FL: input-conditional uncertainty and prediction-label loss. The uncertainty signal is characterised using a learned aleatoric variance estimate together with Monte Carlo (MC) dropout variance and entropy measures, while the loss is computed against the supplied label. We test these signals against additive image noise and persistent random label flips. On ResNet-20 with CIFAR-10 and SVHN under Dirichlet partitions with data that are not independent and identically distributed (non-IID), the two corruption types behave differently. For persistent random label flips, the within-client per-sample area under the receiver operating characteristic curve (AUC) is 0.85 on CIFAR-10 and 0.95 on SVHN for prediction-label loss, while every uncertainty estimator stays at chance (0.49--0.50). This pattern is consistent with the model remaining confident in the underlying image despite the supplied label being wrong. For image noise, expected-entropy uncertainty rises above chance (0.67 on CIFAR-10 and 0.66 on SVHN), while loss responds comparably (0.64 on both). Each signal is therefore the stronger detector for a different corruption: the prediction-label loss for persistent label flips, and expected-entropy uncertainty for image noise, with its advantage becoming apparent as federation-wide corruption prevalence increases. Robust FL data-quality assessment should match the signal to the corruption rather than rely on uncertainty alone across corruption types.