Yunsheng Yuan
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Research Timeline
2026
DPDL: Towards Differential Privacy Preservation in Decentralized Stochastic Learning on Non-IID Data
The paper proposes DPDL, a novel differential privacy algorithm for decentralized stochastic learning on non-IID data, which uses similarity-based calibration of perturbed cross-gradients to achieve privacy preservation and maintain training efficiency.
Highlighted terms show continued research focus across papers