FedCap-Priv: Geometry-Aware Privacy and Bandwidth-Efficient Routing for Federated Capsule Learning
- 1Faculty of Data Science, City University of Macau, Macao 999078, China
Abstract
Capsule networks explicitly encode pose and part–whole structure, making them attractive for heterogeneous visual and speech data but creating structured messages and substantial communication costs in federated learning. We present FedCap-Priv, a federated capsule framework that jointly addresses transcript privacy, predictive utility, and uplink cost through three capsule-specific procedures. Secure Routing by Agreement (SeRBA) retains dynamic routing on each client and replaces direct vote exchange with compact directional and low-rank agreement sketches. Pose-Sensitive Differential Privacy (PS-DP) clips each layer sketch and applies anisotropic Gaussian perturbation aligned with pose variability. Our client-level Rényi-DP analysis accounts for data-dependent means and covariances, visible selection indices, layer composition, client participation, and temporal composition. Sparsity-Guided Partial Aggregation (SGPA) selects salient parent blocks after perturbation and uses error feedback to reduce communication. Across MNIST, Fashion-MNIST, CIFAR-10, and Speech Commands, FedCap-Priv improves accuracy over isotropic FedDP and lowers reconstruction scores under DLG, iDLG, and cosine-TV attacks. On CIFAR-10, it reaches 73.9% accuracy versus 68.9% for isotropic FedDP while reducing the mean participating-client uplink from 220 KB to 22.1 KB per round, a 9.95-fold reduction. The sketch interface supports vector- and matrix-pose capsules and can be combined with secure aggregation.
Related
- Projection-Based Federated Learning on Compact Submanifolds with Geometry-Independent Differential Privacy
- PA-CFL: Privacy-Preserving Adaptive Clustered Federated Learning Under Heterogeneous Data
- Privacy-Preserving Over-the-Air Federated Learning over Cell-Free Massive MIMO System with User-Centric Clustering
- Federated deep learning for privacy-preserving cardiovascular disease risk prediction
- BCFL-DAI-PUB: Blockchain-integrated federated learning with dynamic adaptive incentives for privacy-utility balanced credit risk modelling
BibTeX
@article{li2026fedcappriv,
title = {{FedCap-Priv: Geometry-Aware Privacy and Bandwidth-Efficient Routing for Federated Capsule Learning}},
author = {Yantao Li and Zijie Pan},
journal = {Mathematics},
year = {2026},
month = nov,
doi = {10.3390/math14213993},
url = {https://www.mdpi.com/2227-7390/14/21/3993},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - FedCap-Priv: Geometry-Aware Privacy and Bandwidth-Efficient Routing for Federated Capsule Learning
AU - Yantao Li
AU - Zijie Pan
PY - 2026
DA - 2026/11/02
JO - Mathematics
DO - 10.3390/math14213993
UR - https://www.mdpi.com/2227-7390/14/21/3993
AB - Capsule networks explicitly encode pose and part–whole structure, making them attractive for heterogeneous visual and speech data but creating structured messages and substantial communication costs in federated learning. We present FedCap-Priv, a federated capsule framework that jointly addresses transcript privacy, predictive utility, and uplink cost through three capsule-specific procedures. Secure Routing by Agreement (SeRBA) retains dynamic routing on each client and replaces direct vote exchange with compact directional and low-rank agreement sketches. Pose-Sensitive Differential Privacy (PS-DP) clips each layer sketch and applies anisotropic Gaussian perturbation aligned with pose variability. Our client-level Rényi-DP analysis accounts for data-dependent means and covariances, visible selection indices, layer composition, client participation, and temporal composition. Sparsity-Guided Partial Aggregation (SGPA) selects salient parent blocks after perturbation and uses error feedback to reduce communication. Across MNIST, Fashion-MNIST, CIFAR-10, and Speech Commands, FedCap-Priv improves accuracy over isotropic FedDP and lowers reconstruction scores under DLG, iDLG, and cosine-TV attacks. On CIFAR-10, it reaches 73.9% accuracy versus 68.9% for isotropic FedDP while reducing the mean participating-client uplink from 220 KB to 22.1 KB per round, a 9.95-fold reduction. The sketch interface supports vector- and matrix-pose capsules and can be combined with secure aggregation.
SN - 2227-7390
ER -