Skip to main navigation
Skip to search
Skip to main content
Princeton University Home
Help & FAQ
Link opens in a new tab
Search content at Princeton University
Home
Profiles
Research units
Facilities
Projects
Research output
Press/Media
Random Orthogonalization for Private Wireless Federated Learning
Sadaf Ul Zuhra
, Mohamed Seif
, Karim Banawan
,
H. Vincent Poor
Electrical and Computer Engineering
Center for Statistics & Machine Learning
High Meadows Environmental Institute
NextG
Research output
:
Chapter in Book/Report/Conference proceeding
›
Conference contribution
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Random Orthogonalization for Private Wireless Federated Learning'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Local Model
100%
Orthogonalization
100%
Wireless Federated Learning
100%
Privacy Level
75%
Parameter Server
75%
Global Model
50%
Machine Learning Models
50%
Numerical Results
25%
Convergence Rate
25%
Multiple Access Channel
25%
Antenna
25%
Massive multiple-input multiple-output (mMIMO)
25%
Wireless
25%
Channel Gain
25%
Number of Antennas
25%
Number of Users
25%
Classification Task
25%
Local Update
25%
Privacy Leakage
25%
Single Antennas
25%
Privacy Metrics
25%
MIMO multiple Access Channel
25%
Federated Learning
25%
Local Differential Privacy
25%
Noise Injection
25%
Communication Rounds
25%
Computer Science
Orthogonalization
100%
Parameter Server
100%
Federated machine learning
100%
Antennas
100%
Multiple Access Channel
66%
Machine Learning Model
66%
Differential Privacy
33%
Convergence Rate
33%
Classification Task
33%
Privacy Leakage
33%
Massive MIMO
33%