# Differentially Private Federated Learning With Time-Adaptive Privacy Spending

arXiv: https://arxiv.org/abs/2502.18706 · HTML: https://mlsanity.com/paper/2502.18706/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Builds on (most cited first, 26 of 26)

- [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)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [Differentially Private Learning with Adaptive Clipping](https://mlsanity.com/paper/1905.03871/) (2019)
- [A Hybrid Approach to Privacy-Preserving Federated Learning](https://mlsanity.com/paper/1812.03224/) (2018)
- [R'enyi Differential Privacy of the Sampled Gaussian Mechanism](https://mlsanity.com/paper/1908.10530/) (2019)
- [Practical Secure Aggregation for Federated Learning on User-Held Data](https://mlsanity.com/paper/1611.04482/) (2016)
- [LDP-Fed: Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2006.03637/) (2020)
- [When the Curious Abandon Honesty: Federated Learning Is Not Private](https://mlsanity.com/paper/2112.02918/) (2021)
- [FedALA: Adaptive Local Aggregation for Personalized Federated Learning](https://mlsanity.com/paper/2212.01197/) (2022)
- [AdaCliP: Adaptive Clipping for Private SGD](https://mlsanity.com/paper/1908.07643/) (2019)
- [Training Production Language Models without Memorizing User Data](https://mlsanity.com/paper/2009.10031/) (2020)
- [Private Adaptive Optimization with Side Information](https://mlsanity.com/paper/2202.05963/) (2022)
- [Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy](https://mlsanity.com/paper/2202.07178/) (2022)
- [Heterogeneous Differential Privacy](https://mlsanity.com/paper/1504.06998/) (2015)
- [Have it your way: Individualized Privacy Assignment for DP-SGD](https://mlsanity.com/paper/2303.17046/) (2023)
- [Beyond Uniform Lipschitz Condition in Differentially Private Optimization](https://mlsanity.com/paper/2206.10713/) (2022)
- [Band-limited Training and Inference for Convolutional Neural Networks](https://mlsanity.com/paper/1911.09287/) (2019)
- [Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning](https://mlsanity.com/paper/2406.03519/) (2024)

## Built on by (most cited first, 5 of 5)

- [Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy](https://mlsanity.com/paper/2505.13655/) (2025)
- [Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation](https://mlsanity.com/paper/2509.25906/) (2025)
- [ALPINE: Closed-Loop Adaptive Privacy Budget Allocation for Mobile Edge Crowdsensing](https://mlsanity.com/paper/2510.17162/) (2025)
- [An Adaptive Differentially Private Federated Learning Framework](https://mlsanity.com/paper/2602.06838/) (2026)
- [UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment](https://mlsanity.com/paper/2605.08288/) (2026)

## Abstract (arXiv)

Federated learning (FL) with differential privacy (DP) provides a framework for collaborative machine learning, enabling clients to train a shared model while adhering to strict privacy constraints. The framework allows each client to have an individual privacy guarantee, e.g., by adding different amounts of noise to each client's model updates. One underlying assumption is that all clients spend their privacy budgets uniformly over time (learning rounds). However, it has been shown in the literature that learning in early rounds typically focuses on more coarse-grained features that can be learned at lower signal-to-noise ratios while later rounds learn fine-grained features that benefit from higher signal-to-noise ratios. Building on this intuition, we propose a time-adaptive DP-FL framework that expends the privacy budget non-uniformly across both time and clients. Our framework enables each client to save privacy budget in early rounds so as to be able to spend more in later rounds when additional accuracy is beneficial in learning more fine-grained features. We theoretically prove utility improvements in the case that clients with stricter privacy budgets spend budgets unevenly across rounds, compared to clients with more relaxed budgets, who have sufficient budgets to distribute their spend more evenly. Our practical experiments on standard benchmark datasets support our theoretical results and show that, in practice, our algorithms improve the privacy-utility trade-offs compared to baseline schemes.