# FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification

arXiv: https://arxiv.org/abs/2508.17431 · HTML: https://mlsanity.com/paper/2508.17431/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 62 references that are in the map.
- First posted on arXiv 24 Aug 2025.

## Builds on (most cited first, 28 of 28)

- [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)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space](https://mlsanity.com/paper/2103.06030/) (2021)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [The Convergence of Sparsified Gradient Methods](https://mlsanity.com/paper/1809.10505/) (2018)
- [Model Pruning Enables Efficient Federated Learning on Edge Devices](https://mlsanity.com/paper/1909.12326/) (2019)
- [Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification](https://mlsanity.com/paper/2001.01526/) (2020)
- [Personalized Federated Learning with First Order Model Optimization](https://mlsanity.com/paper/2012.08565/) (2020)
- [Camera-aware Proxies for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2012.10674/) (2020)
- [Unsupervised Person Re-identification by Soft Multilabel Learning](https://mlsanity.com/paper/1903.06325/) (2019)
- [Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning](https://mlsanity.com/paper/2110.08394/) (2021)
- [Intra-Inter Camera Similarity for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11658/) (2021)
- [Performance Optimization for Federated Person Re-identification via Benchmark Analysis](https://mlsanity.com/paper/2008.11560/) (2020)
- [Unsupervised Person Re-identification by Deep Learning Tracklet Association](https://mlsanity.com/paper/1809.02874/) (2018)
- [Dynamic Label Graph Matching for Unsupervised Video Re-Identification](https://mlsanity.com/paper/1709.09297/) (2017)
- [EasyFL: A Low-code Federated Learning Platform For Dummies](https://mlsanity.com/paper/2105.07603/) (2021)
- [Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identification](https://mlsanity.com/paper/2108.06493/) (2021)
- [Deep Association Learning for Unsupervised Video Person Re-identification](https://mlsanity.com/paper/1808.07301/) (2018)
- [Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns](https://mlsanity.com/paper/1803.07293/) (2018)
- [Federated Submodel Optimization for Hot and Cold Data Features](https://mlsanity.com/paper/2109.07704/) (2021)
- [Robust Knowledge Adaptation for Federated Unsupervised Person ReID](https://mlsanity.com/paper/2301.07320/) (2023)

## Abstract (arXiv)

Person re-identification (re-ID) is a fundamental task in intelligent surveillance and public safety. Federated learning (FL) provides a privacy-preserving paradigm for collaborative model training without centralized data collection. However, deploying FL in real-world re-ID systems remains challenging due to statistical heterogeneity caused by non-IID client data and the substantial communication overhead incurred by frequent transmission of large-scale models. To address these challenges, we propose FedKLPR, a lightweight and communication-efficient federated learning framework for person re-ID. FedKLPR consists of three key components. First, KL-Divergence-Guided training, including the KL-Divergence Regularization Loss (KLL) and KL-Divergence-aggregation Weight (KLAW), is introduced to mitigate statistical heterogeneity and improve convergence stability under non-IID settings. Second, unstructured pruning is incorporated to reduce communication overhead, and the Pruning-ratio-aggregation Weight (PRAW) is proposed to measure the relative importance of client parameters after pruning. Together with KLAW, PRAW forms KL-Divergence-Prune Weighted Aggregation (KLPWA), enabling effective aggregation of pruned local models under heterogeneous data distributions. Third, Cross-Round Recovery (CRR) adaptively controls pruning across communication rounds to prevent excessive compression and preserve model accuracy. Experiments on eight benchmark datasets demonstrate that FedKLPR achieves substantial communication savings while maintaining competitive accuracy. Compared with state-of-the-art methods, FedKLPR reduces communication cost by 40%--42% on ResNet-50 while achieving better overall performance.