analiza aiqbench
FedRP introduces a novel framework for federated learning that leverages Gaussian random projection to drastically reduce communication overhead while maintaining strong differential privacy guarantees. By transmitting compressed representations instead of full model updates, this approach mitigates reconstruction attacks and lowers bandwidth requirements without sacrificing accuracy on standard benchmarks like MNIST and CIFAR-10. The method effectively balances the critical triad of model performance, data privacy, and network efficiency for distributed training scenarios.
FedRP: A Communication-Efficient Approach for Differentially Private Federated Learning Using Random Projection
arXiv:2509.10041v2 Announce Type: replace Abstract: Federated learning (FL) enables collaborative model training without centralizing data, but exchanging high-dimensional updates can expose sensitive information and incur substantial communication costs. We present FedRP, a communication-efficient method combining Gaussian random projection with consensus optimization based on the alternating direction method of multipliers (ADMM). In each round, clients project their model parameters into an $m$-dimensional space using a shared random matrix hidden from the server, which aggregates only compressed representations. We establish a high-probability guarantee linking projected-space consensus to proximity among client models and derive an $(\epsilon,\delta)$-differential privacy guarantee for each release under bounded $\ell_2$-sensitivity and a positive lower bound on parameter norms. With randomized parameter vectors and the projection matrix also limits information available to common reconstruction attacks. Experiments on MNIST and CIFAR-10 with LeNet-5 and a custom convolutional network show that FedRP achieves accuracy comparable to FedAvg and consistently exposes noise-perturbed privacy via FedAvg. Because clients transmit $m$ rather than $n$ values per round, FedRP reduces communication by orders of magnitude when $m \ll n$. The results demonstrate a favorable trade-off among accuracy, privacy, and communication efficiency. Code is available at https://github.com/mhnarimani/FedRP
Abstract:Federated learning (FL) enables collaborative model training without centralizing data, but exchanging high-dimensional updates can expose sensitive information and incur substantial communication costs. We present FedRP, a communication-efficient method combining Gaussian random projection with consensus optimization based on the alternating direction method of multipliers (ADMM). In each round, clients project their model parameters into an $m$-dimensional space using a shared random matrix hidden from the server, which aggregates only compressed representations. We establish a high-probability guarantee linking projected-space consensus to proximity among client models and derive an $(\epsilon,\delta)$-differential privacy guarantee for each release under bounded $\ell_2$-sensitivity and a positive lower bound on parameter norms. With randomized parameter vectors and the projection matrix also limits information available to common reconstruction attacks. Experiments on MNIST and CIFAR-10 with LeNet-5 and a custom convolutional network show that FedRP achieves accuracy comparable to FedAvg and consistently exposes noise-perturbed privacy via FedAvg. Because clients transmit $m$ rather than $n$ values per round, FedRP reduces communication by orders of magnitude when $m \ll n$. The results demonstrate a favorable trade-off among accuracy, privacy, and communication efficiency. Code is available at this https URL
Machine Learning (cs.LG)
arXiv:2509.10041 [cs.LG]
(or arXiv:2509.10041v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2509.10041 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 279 cuvinte
