DPDL: Towards Differential Privacy Preservation in Decentralized Stochastic Learning on Non-IID Data

ArXi:2606.04399v1 Announce Type: new In the paradigm of decentralized learning, a group of agents collaborate to train a global model using distributed datasets without a central server. Although the power of collaboration has been verified by many state-of-the-art studies, it entails extensive gradient information exchanging among the agents and thus induces high risk of privacy leakage for the individual agents. Moreover, in real-world applications, the