arXiv Machine Learning By Yilin Xu, Chun Hei Michael Shiu, Chih Wei Ling, Linqi Song

Privacy-Aligned Personalized Federated Learning with Compact Adaptation and Variable-Length Gaussian Communication

Read the original on arXiv Machine Learning →

The paper proposes a privacy‑aligned personalized federated learning method that releases a private client context once and limits repeated adaptation to a fixed coefficient space, thereby reducing dimensionality misalignment. A factorized generator creates an adaptive optimization geometry that reshapes noisy updates, and most of the private‑training benefit is preserved by radial evolution. Variable‑length Gaussian quantization is used for coefficient updates, allowing the quantization error to act as the privacy perturbation and cutting protected uplink communication by a factor of 2.67 on CIFAR‑10 at ε=16 while maintaining comparable future‑client accuracy.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Aug 27

Theoretically Principled Federated Learning for Balancing Privacy and Utility

The paper introduces a general learning framework that protects privacy in federated learning by distorting model parameters, enabling a trade‑off between privacy and utility. The algorithm supports arbitrary privacy measurements and delivers personalized utility‑privacy balances for each parameter, client, and communication round. The authors prove that the gap between their algorithm’s utility loss and the optimal loss is sub‑linear in iterations, provide a convergence rate, and demonstrate empirically that their method outperforms baselines under the same privacy budget.

By Xiaojin Zhang, Wenjie Li, Yiming Li, Wei Chen, Shutao Xia, Qiang Yang
arXiv AI
Aug 18

Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy

arXiv:2509. 10691v3 Announce Type: replace-cross Abstract: Decentralized federated learning enables collaborative model training without a central server, but shared model updates can still leak sensitive information through inversion, reconstruction, and membership inference attacks.

By Fardin Jalil Piran, Zhiling Chen, Yang Zhang, Qianyu Zhou, Jiong Tang, Farhad Imani