Toward Empirical Aspects of Secure Scalar Product

Wang, I-Cheng; Shen, Chih-Hao; Zhan, Justin; Hsu, Tsan-sheng; Liau, Churn‐Jung; Wang, Dawei

doi:10.1109/tsmcc.2009.2016430

Cited by 24 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first is to use techniques based on Secure Scalar Product Protocols (SSPP) (Wang et al 2009;Shundong, Mengyu, and Wenting 2021), which aims to compute the dot product of private vectors of parties. We argue that any existing solutions of SSPP can be used to reconstruct the similarity matrix V of clients in our settings, and we detail one of the existing solutions for scalar product protocal (Du and Zhan 2002) with a discussion on how to adapt it to build the 3DG in the Appendix 1 D.…”

Section: Construction Of 3dg In Flmentioning

confidence: 99%

FedGS: Federated Graph-Based Sampling with Arbitrary Client Availability

Wang

Fan

et al. 2023

AAAI

View full text Add to dashboard Cite

While federated learning has shown strong results in opti- mizing a machine learning model without direct access to the original data, its performance may be hindered by in- termittent client availability which slows down the conver- gence and biases the final learned model. There are significant challenges to achieve both stable and bias-free training un- der arbitrary client availability. To address these challenges, we propose a framework named Federated Graph-based Sam- pling (FEDGS), to stabilize the global model update and mitigate the long-term bias given arbitrary client availabil- ity simultaneously. First, we model the data correlations of clients with a Data-Distribution-Dependency Graph (3DG) that helps keep the sampled clients data apart from each other, which is theoretically shown to improve the approximation to the optimal model update. Second, constrained by the far- distance in data distribution of the sampled clients, we fur- ther minimize the variance of the numbers of times that the clients are sampled, to mitigate long-term bias. To validate the effectiveness of FEDGS, we conduct experiments on three datasets under a comprehensive set of seven client availability modes. Our experimental results confirm FEDGS’s advantage in both enabling a fair client-sampling scheme and improving the model performance under arbitrary client availability. Our code is available at https://github.com/WwZzz/FedGS.

show abstract

Section: Construction Of 3dg In Flmentioning

confidence: 99%