Skip to content

ParallelProcessingLab/Federated-Learning-Example

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Federated-Learning-Example

A simple example for federated learning in java

Simple run output:

=== Federated Learning Starts ===

--- Round 1 ---
Reward Rate: 0.05
Global Accuracy after aggregation: 0.9124

--- Round 2 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9029

--- Round 3 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8970

--- Round 4 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8918

--- Round 5 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8961

--- Round 6 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9015

--- Round 7 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9010

--- Round 8 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8974

--- Round 9 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9032

--- Round 10 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9145

--- Round 11 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9104

--- Round 12 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9023

--- Round 13 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8978

--- Round 14 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8733

--- Round 15 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9127

--- Round 16 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8818

--- Round 17 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9044

--- Round 18 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8925

--- Round 19 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8883

--- Round 20 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8958

--- Round 21 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9032

--- Round 22 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9006

--- Round 23 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8959

--- Round 24 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9160

--- Round 25 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9093

--- Round 26 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9029

--- Round 27 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9028

--- Round 28 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8830

--- Round 29 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8934

--- Round 30 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9142

--- Round 31 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9047

--- Round 32 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9052

--- Round 33 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8907

--- Round 34 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9043

--- Round 35 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9075

--- Round 36 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9086

--- Round 37 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9018

--- Round 38 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8976

--- Round 39 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9045

--- Round 40 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9100

--- Round 41 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9042

--- Round 42 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9014

--- Round 43 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9022

--- Round 44 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8977

--- Round 45 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9001

--- Round 46 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9155

--- Round 47 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8947

--- Round 48 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8967

--- Round 49 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9020

--- Round 50 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8978

--- Round 51 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9037

--- Round 52 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9021

--- Round 53 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8982

--- Round 54 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8970

--- Round 55 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9139

--- Round 56 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9050

--- Round 57 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8804

--- Round 58 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8942

--- Round 59 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8983

--- Round 60 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9081

--- Round 61 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9121

--- Round 62 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9017

--- Round 63 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9086

--- Round 64 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9020

--- Round 65 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9106

--- Round 66 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9074

--- Round 67 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9081

--- Round 68 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8937

--- Round 69 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8945

--- Round 70 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8991

--- Round 71 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9160

--- Round 72 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8921

--- Round 73 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8978

--- Round 74 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9006

--- Round 75 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8936

--- Round 76 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8987

--- Round 77 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9138

--- Round 78 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9066

--- Round 79 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9028

--- Round 80 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.8800

--- Round 81 ---
Reward Rate: 0.1
Global Accuracy after aggregation: 0.9211

 Target Accuracy Achieved! Training Complete.
=== Federated Learning Ends ===

About

A simple example for federated learning in java

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages