PADP-FedMeta: A personalized and adaptive differentially private federated meta learning mechanism for AIoT

Dong, Fang; Ge, Xinghua; Li, Qinya; Zhang, Jinghui; Shen, Dian; Liu, Siqi; Liu, Xiao; Li, Gang; Wang, Fan; Luo, Junzhou

doi:10.1016/j.sysarc.2022.102754

Cited by 7 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can broadly classify the works that consider formal privacy/security guarantees into two categories. First, the works that use differential privacy as the mechanism to provide privacy guarantees, such as the FL approaches combined with DP [6,20,30]. These works only consider uniform privacy guarantees, lacking personalized privacy where sites can independently select their privacy budgets.…”

Section: Related Workmentioning

confidence: 99%

PubSub-ML: A Model Streaming Alternative to Federated Learning

Gondara

Wang

2023

PoPETs

View full text Add to dashboard Cite

Federated learning is a decentralized learning framework where participating sites are engaged in a tight collaboration, forcing them into symmetric sharing and the agreement in terms of data samples, feature spaces, model types and architectures, privacy settings, and training processes. We propose PubSub-ML, Publish-Subscribe for Machine Learning, as a solution in a loose collaboration setting where each site maintains local autonomy on these decisions. In PubSub-ML, each site is either a publisher or a subscriber or both. The publishers publish differentially private machine learning models and the subscribers subscribe to published models in order to construct customized models for local use, essentially benefiting from other sites' data by distilling knowledge from publishers' models while respecting data privacy. The term “model streaming” comes from the extension of PubSub-ML to decentralized data streams with concept drift. Our extensive empirical evaluation shows that PubSub-ML outperforms federated learning methods by a significant margin.

show abstract

Section: Related Workmentioning

confidence: 99%