# FedSM: Robust Semantics-Guided Feature Mixup for Bias Reduction in Federated Learning with Long-Tail Data

arXiv: https://arxiv.org/abs/2510.27240 · HTML: https://mlsanity.com/paper/2510.27240/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://mlsanity.com/paper/2007.07481/) (2020)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2106.05001/) (2021)
- [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://mlsanity.com/paper/2009.01974/) (2020)
- [CLIPood: Generalizing CLIP to Out-of-Distributions](https://mlsanity.com/paper/2302.00864/) (2023)
- [Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features](https://mlsanity.com/paper/2204.13399/) (2022)
- [Federated Learning with Fair Averaging](https://mlsanity.com/paper/2104.14937/) (2021)
- [Federated learning with class imbalance reduction](https://mlsanity.com/paper/2011.11266/) (2020)
- [Fed-Focal Loss for imbalanced data classification in Federated Learning](https://mlsanity.com/paper/2011.06283/) (2020)
- [FLGo: A Fully Customizable Federated Learning Platform](https://mlsanity.com/paper/2306.12079/) (2023)
- [Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup](https://mlsanity.com/paper/2305.16817/) (2023)
- [Behavior Mimics Distribution: Combining Individual and Group Behaviors for Federated Learning](https://mlsanity.com/paper/2106.12300/) (2021)
- [FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift](https://mlsanity.com/paper/2507.04781/) (2025)

## Abstract (arXiv)

Federated Learning (FL) enables collaborative model training across decentralized clients without sharing private data. However, FL suffers from biased global models due to non-IID and long-tail data distributions. We propose FedSM, a novel client-centric framework that mitigates this bias through semantics-guided feature mixup and lightweight classifier retraining. FedSM uses a pretrained image-text-aligned model to compute category-level semantic relevance, guiding the category selection of local features to mix-up with global prototypes to generate class-consistent pseudo-features. These features correct classifier bias, especially when data are heavily skewed. To address the concern of potential domain shift between the pretrained model and the data, we propose probabilistic category selection, enhancing feature diversity to effectively mitigate biases. All computations are performed locally, requiring minimal server overhead. Extensive experiments on long-tail datasets with various imbalanced levels demonstrate that FedSM consistently outperforms state-of-the-art methods in accuracy, with high robustness to domain shift and computational efficiency.