{"ID":2826002,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20814","arxiv_id":"2512.20814","title":"FedMPDD: Communication-Efficient Federated Learning with Privacy Preservation Attributes via Projected Directional Derivative","abstract":"This paper introduces \\texttt{FedMPDD} (\\textbf{Fed}erated Learning via \\textbf{M}ulti-\\textbf{P}rojected \\textbf{D}irectional \\textbf{D}erivatives), a novel algorithm that simultaneously optimizes bandwidth utilization and enhances privacy in Federated Learning. The core idea of \\texttt{FedMPDD} is to encode each client's high-dimensional gradient by computing its directional derivatives along multiple random vectors. This compresses the gradient into a much smaller message, significantly reducing uplink communication costs from $\\mathcal{O}(d)$ to $\\mathcal{O}(m)$, where $m \\ll d$. The server then decodes the aggregated information by projecting it back onto the same random vectors. Our key insight is that averaging multiple projections overcomes the dimension-dependent convergence limitations of a single projection. We provide a rigorous theoretical analysis, establishing that \\texttt{FedMPDD} converges at a rate of $\\mathcal{O}(1/\\sqrt{K})$, matching the performance of FedSGD. Furthermore, we demonstrate that our method provides some inherent privacy against gradient inversion attacks due to the geometric properties of low-rank projections, offering a tunable privacy-utility trade-off controlled by the number of projections. Extensive experiments on benchmark datasets validate our theory and demonstrates our results.","short_abstract":"This paper introduces \\texttt{FedMPDD} (\\textbf{Fed}erated Learning via \\textbf{M}ulti-\\textbf{P}rojected \\textbf{D}irectional \\textbf{D}erivatives), a novel algorithm that simultaneously optimizes bandwidth utilization and enhances privacy in Federated Learning. The core idea of \\texttt{FedMPDD} is to encode each clie...","url_abs":"https://arxiv.org/abs/2512.20814","url_pdf":"https://arxiv.org/pdf/2512.20814v1","authors":"[\"Mohammadreza Rostami\",\"Solmaz S. Kia\"]","published":"2025-12-23T22:25:11Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}