# Trading Off Privacy, Utility and Efficiency in Federated Learning

arXiv: https://arxiv.org/abs/2209.00230 · HTML: https://mlsanity.com/paper/2209.00230/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 62 references that are in the map.
- First posted on arXiv 1 Sep 2022.

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

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [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)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/1909.11875/) (2019)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Distributed learning of deep neural network over multiple agents](https://mlsanity.com/paper/1810.06060/) (2018)
- [A Hybrid Approach to Privacy-Preserving Federated Learning](https://mlsanity.com/paper/1812.03224/) (2018)
- [SecureBoost: A Lossless Federated Learning Framework](https://mlsanity.com/paper/1901.08755/) (2019)
- [LDP-Fed: Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2006.03637/) (2020)
- [Label Leakage and Protection in Two-party Split Learning](https://mlsanity.com/paper/2102.08504/) (2021)
- [Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD](https://mlsanity.com/paper/1810.08313/) (2018)
- [Breaking the Communication-Privacy-Accuracy Trilemma](https://mlsanity.com/paper/2007.11707/) (2020)
- [No Free Lunch Theorem for Security and Utility in Federated Learning](https://mlsanity.com/paper/2203.05816/) (2022)
- [Federated Doubly Stochastic Kernel Learning for Vertically Partitioned Data](https://mlsanity.com/paper/2008.06197/) (2020)
- [Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretability](https://mlsanity.com/paper/2111.10934/) (2021)
- [Fast Federated Learning by Balancing Communication Trade-Offs](https://mlsanity.com/paper/2105.11028/) (2021)
- [Constraining Variational Inference with Geometric Jensen-Shannon Divergence](https://mlsanity.com/paper/2006.10599/) (2020)
- [Federated Deep Learning with Bayesian Privacy](https://mlsanity.com/paper/2109.13012/) (2021)
- [Sharing Models or Coresets: A Study based on Membership Inference Attack](https://mlsanity.com/paper/2007.02977/) (2020)

## Built on by (most cited first, 30 of 33)

- [Vertical Federated Learning: Concepts, Advances and Challenges](https://mlsanity.com/paper/2211.12814/) (2022)
- [Federated Continual Learning via Knowledge Fusion: A Survey](https://mlsanity.com/paper/2312.16475/) (2023)
- [Advances and Open Challenges in Federated Foundation Models](https://mlsanity.com/paper/2404.15381/) (2024)
- [A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency](https://mlsanity.com/paper/2307.10655/) (2023)
- [A Survey for Federated Learning Evaluations: Goals and Measures](https://mlsanity.com/paper/2308.11841/) (2023)
- [FlexOlmo: Open Language Models for Flexible Data Use](https://mlsanity.com/paper/2507.07024/) (2025)
- [Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey](https://mlsanity.com/paper/2405.17495/) (2024)
- [Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learning](https://mlsanity.com/paper/2305.00312/) (2023)
- [A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learning](https://mlsanity.com/paper/2209.03885/) (2022)
- [FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscation](https://mlsanity.com/paper/2301.12623/) (2023)
- [FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfer](https://mlsanity.com/paper/2405.02685/) (2024)
- [Towards Achieving Near-optimal Utility for Privacy-Preserving Federated Learning via Data Generation and Parameter Distortion](https://mlsanity.com/paper/2305.04288/) (2023)
- [Theoretically Principled Federated Learning for Balancing Privacy and Utility](https://mlsanity.com/paper/2305.15148/) (2023)
- [A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning](https://mlsanity.com/paper/2305.18400/) (2023)
- [Fake It Till Make It: Federated Learning with Consensus-Oriented Generation](https://mlsanity.com/paper/2312.05966/) (2023)
- [A Survey on Contribution Evaluation in Vertical Federated Learning](https://mlsanity.com/paper/2405.02364/) (2024)
- [Probably Approximately Correct Federated Learning](https://mlsanity.com/paper/2304.04641/) (2023)
- [HiFGL: A Hierarchical Framework for Cross-silo Cross-device Federated Graph Learning](https://mlsanity.com/paper/2406.10616/) (2024)
- [Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks](https://mlsanity.com/paper/2504.17421/) (2025)
- [Federated Learning Empowered by Generative Content](https://mlsanity.com/paper/2312.05807/) (2023)
- [A Game-theoretic Framework for Privacy-preserving Federated Learning](https://mlsanity.com/paper/2304.05836/) (2023)
- [Automated discovery of trade-off between utility, privacy and fairness in machine learning models](https://mlsanity.com/paper/2311.15691/) (2023)
- [NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA](https://mlsanity.com/paper/2411.03730/) (2024)
- [Hyperparameter Optimization for SecureBoost via Constrained Multi-Objective Federated Learning](https://mlsanity.com/paper/2404.04490/) (2024)
- [Against Multifaceted Graph Heterogeneity via Asymmetric Federated Prompt Learning](https://mlsanity.com/paper/2411.02003/) (2024)
- [FedAdOb: Privacy-Preserving Federated Deep Learning with Adaptive Obfuscation](https://mlsanity.com/paper/2406.01085/) (2024)
- [Optimal Defenses Against Gradient Reconstruction Attacks](https://mlsanity.com/paper/2411.03746/) (2024)
- [Harmonizing Generalization and Personalization in Ring-topology Decentralized Federated Learning](https://mlsanity.com/paper/2504.19103/) (2025)
- [A Survey of Personalized Federated Foundation Models for Privacy-Preserving Recommendation](https://mlsanity.com/paper/2506.11563/) (2025)
- [Balancing Privacy-Quality-Efficiency in Federated Learning through Round-Based Interleaving of Protection Techniques](https://mlsanity.com/paper/2603.05158/) (2026)

## Abstract (arXiv)

Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the opposing requirements in preserving textitprivacy and maintaining high model textitutility. In addition, it is a mandate for a federated learning system to achieve high textitefficiency in order to enable large-scale model training and deployment. We propose a unified federated learning framework that reconciles horizontal and vertical federated learning. Based on this framework, we formulate and quantify the trade-offs between privacy leakage, utility loss, and efficiency reduction, which leads us to the No-Free-Lunch (NFL) theorem for the federated learning system. NFL indicates that it is unrealistic to expect an FL algorithm to simultaneously provide excellent privacy, utility, and efficiency in certain scenarios. We then analyze the lower bounds for the privacy leakage, utility loss and efficiency reduction for several widely-adopted protection mechanisms including textitRandomization, textitHomomorphic Encryption, textitSecret Sharing and textitCompression. Our analysis could serve as a guide for selecting protection parameters to meet particular requirements.