# An Adaptive Differentially Private Federated Learning Framework

arXiv: https://arxiv.org/abs/2602.06838 · HTML: https://mlsanity.com/paper/2602.06838/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 34 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 14 of 14)

- [Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits](https://mlsanity.com/paper/2411.18704/) (2024)
- [Federated Semi-supervised Medical Image Classification via Inter-client Relation Matching](https://mlsanity.com/paper/2106.08600/) (2021)
- [Dynamic Sparse Training with Structured Sparsity](https://mlsanity.com/paper/2305.02299/) (2023)
- [One-shot Empirical Privacy Estimation for Federated Learning](https://mlsanity.com/paper/2302.03098/) (2023)
- [Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy](https://mlsanity.com/paper/2202.07178/) (2022)
- [Distributed Distributionally Robust Optimization with Non-Convex Objectives](https://mlsanity.com/paper/2210.07588/) (2022)
- [ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy](https://mlsanity.com/paper/2308.12210/) (2023)
- [Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning](https://mlsanity.com/paper/2406.03519/) (2024)
- [Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy](https://mlsanity.com/paper/2305.00873/) (2023)
- [Differentially Private Federated Learning With Time-Adaptive Privacy Spending](https://mlsanity.com/paper/2502.18706/) (2025)
- [Belt and Braces: When Federated Learning Meets Differential Privacy](https://mlsanity.com/paper/2404.18814/) (2024)
- [Cellular Traffic Prediction via Byzantine-robust Asynchronous Federated Learning](https://mlsanity.com/paper/2505.19263/) (2025)
- [Camel: Communication-Efficient and Maliciously Secure Federated Learning in the Shuffle Model of Differential Privacy](https://mlsanity.com/paper/2410.03407/) (2024)
- [Harnessing Sparsification in Federated Learning: A Secure, Efficient, and Differentially Private Realization](https://mlsanity.com/paper/2511.07123/) (2025)

## Abstract (arXiv)

Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments, device heterogeneity and non-independent and identically distributed (Non-IID) data often lead to unstable and biased gradient. When differential privacy is enforced, conventional fixed gradient clipping and Gaussian noise injection may further amplify gradient perturbations, resulting in training oscillation and degraded model performance. To address these challenges, we propose an adaptive differentially private federated learning framework that explicitly targets model efficiency under heterogeneous and privacy-constrained settings. On the client side, a lightweight local dimensionality reduction module is introduced to learn reduced-dimensional intermediate representations and produce more structured gradients during backpropagation, thereby mitigating noise amplification during local optimization. On the server side, an adaptive gradient clipping strategy dynamically adjusts clipping thresholds based on historical update statistics to avoid over-clipping and noise domination. Furthermore, a constraint-aware robust aggregation mechanism is designed to suppress unreliable or noise-dominated client updates and stabilize global optimization. Extensive experiments on CIFAR-10, SVHN, and STL-10 demonstrate that the proposed method consistently improves convergence stability and classification performance under differential privacy.