Privacy preservation in Distributed Deep Learning: A survey on Distributed Deep Learning, privacy preservation techniques used and interesting research directions
E Antwi-Boasiako, S Zhou, Y Liao, Q Liu… - Journal of Information …, 2021 - Elsevier
Abstract Distributed or Collaborative Deep Learning, has recently gained more recognition
due to its major advantage of allowing two or more learning participants to contribute and …
due to its major advantage of allowing two or more learning participants to contribute and …
DP-ADMM: ADMM-based distributed learning with differential privacy
Alternating direction method of multipliers (ADMM) is a widely used tool for machine
learning in distributed settings where a machine learning model is trained over distributed …
learning in distributed settings where a machine learning model is trained over distributed …
Privacy-preserving average consensus via state decomposition
Y Wang - IEEE Transactions on Automatic Control, 2019 - ieeexplore.ieee.org
Average consensus underpins key functionalities of distributed systems ranging from
distributed information fusion, decision-making, distributed optimization, to load balancing …
distributed information fusion, decision-making, distributed optimization, to load balancing …
A critical overview of privacy-preserving approaches for collaborative forecasting
Cooperation between different data owners may lead to an improvement in forecast quality—
for instance, by benefiting from spatiotemporal dependencies in geographically distributed …
for instance, by benefiting from spatiotemporal dependencies in geographically distributed …
Tailoring gradient methods for differentially private distributed optimization
Decentralized optimization is gaining increased traction due to its widespread applications
in large-scale machine learning and multiagent systems. The same mechanism that enables …
in large-scale machine learning and multiagent systems. The same mechanism that enables …
Communication-computation efficient secure aggregation for federated learning
Federated learning has been spotlighted as a way to train neural networks using distributed
data with no need for individual nodes to share data. Unfortunately, it has also been shown …
data with no need for individual nodes to share data. Unfortunately, it has also been shown …
FedNew: A communication-efficient and privacy-preserving Newton-type method for federated learning
Newton-type methods are popular in federated learning due to their fast convergence. Still,
they suffer from two main issues, namely: low communication efficiency and low privacy due …
they suffer from two main issues, namely: low communication efficiency and low privacy due …
A privacy preserving distributed optimization algorithm for economic dispatch over time-varying directed networks
The economic dispatch problem (EDP) plays a fundamental and significant role in smart
grids. Its purpose is to decide the output power of every generator in smart grids for …
grids. Its purpose is to decide the output power of every generator in smart grids for …
Two kinds of decentralized robust economic dispatch framework combined distribution network and multi-microgrids
X Zhou, Q Ai, M Yousif - Applied energy, 2019 - Elsevier
This paper describes two kinds of decentralized economic dispatch framework for the
coordinated operation of multi-microgrids in a distribution network. Considering the high …
coordinated operation of multi-microgrids in a distribution network. Considering the high …
Enhancement of opacity for distributed state estimation in cyber–physical systems
L An, GH Yang - Automatica, 2022 - Elsevier
Opacity, a confidentiality property that characterizes whether a “secret” of a system can be
inferred by an outside intruder, is an increasing concern in cyber–physical systems (CPSs) …
inferred by an outside intruder, is an increasing concern in cyber–physical systems (CPSs) …