# Private Aggregation in Hierarchical Wireless Federated Learning with Partial and Full Collusion

arXiv: https://arxiv.org/abs/2306.14088 · HTML: https://mlsanity.com/paper/2306.14088/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 25 Jun 2023.

## Builds on (most cited first, 20 of 20)

- [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)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Error Feedback Fixes SignSGD and other Gradient Compression Schemes](https://mlsanity.com/paper/1901.09847/) (2019)
- [TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning](https://mlsanity.com/paper/1705.07878/) (2017)
- [Gradient Inversion with Generative Image Prior](https://mlsanity.com/paper/2110.14962/) (2021)
- [Hierarchical Federated Learning Across Heterogeneous Cellular Networks](https://mlsanity.com/paper/1909.02362/) (2019)
- [Natural Compression for Distributed Deep Learning](https://mlsanity.com/paper/1905.10988/) (2019)
- [Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning](https://mlsanity.com/paper/2002.04156/) (2020)
- [Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy](https://mlsanity.com/paper/1806.00939/) (2018)
- [LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning](https://mlsanity.com/paper/2109.14236/) (2021)
- [FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning](https://mlsanity.com/paper/2009.11248/) (2020)
- [CodedPaddedFL and CodedSecAgg: Straggler Mitigation and Secure Aggregation in Federated Learning](https://mlsanity.com/paper/2112.08909/) (2021)
- [Information Theoretic Secure Aggregation with User Dropouts](https://mlsanity.com/paper/2101.07750/) (2021)
- [SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning](https://mlsanity.com/paper/2203.13060/) (2022)
- [Foundations of User-Centric Cell-Free Massive MIMO](https://mlsanity.com/paper/2108.02541/) (2021)
- [SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guarantees](https://mlsanity.com/paper/2202.04169/) (2022)
- [Semi-Federated Learning](https://mlsanity.com/paper/2003.12795/) (2020)
- [A Survey on User-Centric Cell-Free Massive MIMO Systems](https://mlsanity.com/paper/2104.13667/) (2021)
- [Communication Efficient Secret Sharing](https://mlsanity.com/paper/1505.07515/) (2015)

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

- [Fundamental Limits of Hierarchical Secure Aggregation with Cyclic User Association](https://mlsanity.com/paper/2503.04564/) (2025)
- [Hierarchical Secure Aggregation with Heterogeneous Security Constraints and Arbitrary User Collusion](https://mlsanity.com/paper/2507.14768/) (2025)
- [Information-Theoretic Decentralized Secure Aggregation with Passive Collusion Resilience](https://mlsanity.com/paper/2508.00596/) (2025)
- [Federated One-Shot Learning with Data Privacy and Objective-Hiding](https://mlsanity.com/paper/2504.21182/) (2025)
- [Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning](https://mlsanity.com/paper/2506.09870/) (2025)

## Abstract (arXiv)

In federated learning, a federator coordinates the training of a model, e.g., a neural network, on privately owned data held by several participating clients. The gradient descent algorithm, a well-known and popular iterative optimization procedure, is run to train the model. Every client computes partial gradients based on their local data and sends them to the federator, which aggregates the results and updates the model. Privacy of the clients' data is a major concern. In fact, it is shown that observing the partial gradients can be enough to reveal the clients' data. Existing literature focuses on private aggregation schemes that tackle the privacy problem in federated learning in settings where all users are connected to each other and to the federator. In this paper, we consider a hierarchical wireless system architecture in which the clients are connected to base stations; the base stations are connected to the federator either directly or through relays. We examine settings with and without relays, and derive fundamental limits on the communication cost under information-theoretic privacy with different collusion assumptions. We introduce suitable private aggregation schemes tailored for these settings whose communication costs are multiplicative factors away from the derived bounds.