Random walk with restart algorithms

Question

0.00/5 (No votes)

See more:

Hi folks,

I am running an exercise of Social network analysis using one of the data mining packages. I stuck at a point on how to understand Random Walk with Restart algorithm that was used by the package I am using in my analysis.

Anyone can help me in this matter and provide me with examples?

Thank you,

What I have tried:

Reading a lot about this topic

Posted 19-Apr-16 0:11am

Member 12470111

Updated 19-Apr-16 1:50am

Add a Solution

1 solution

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

W∴ Balboos, *GHB* · Answer 1 · 2016-04-19T01:50:00

Solution 1

I'll make the assumption that their view of a restart algorithm is the same as I used for some Monte-Carlo simulations i did some years ago (surface interactions an nearest neighbor effects).

When I initialized the random number generator I did not use a random seed (like clock time) but a specific value. I could then modify parameters and restart the same random sequence with a different degree of interaction by using the same seed. Random number generators form a long non-repeating sequence based upon an initial seed value.

I could also use a different seed value and rerun the data - giving me a two-dimensional view. Good for a publication or two.

Of course, the 'manual' for the application could give you a definitive answer.

Posted 19-Apr-16 1:50am

W∴ Balboos, GHB

Comments

Member 12470111 20-Apr-16 3:50am

I would like thank you for your feedback and quick response. The application manual mentioned only one thing 'Authority score is calculated using Random Walk with Restart', Below is a sample group with 3 members only and the results generated by the tool. Could you please help me to reach to Authority scores calculations ?

Rawdata:
A_Number, B_Number, Duration(Link Weight)
599022347, 599022063, 18
599022308, 599022063, 10

Results by the tool:

Group_Size, Group_Density, Group_KernelDensity, Group_CoreNodesFraction
3, 0.333333, 0.666667, 1

NodeNumber, CoreNode, Authoirty_Score, InDegree, OutDegree
599022063, 1, 0.588558, 2, 0
599022308, 1, 0.205721, 0, 1
599022347, 1, 0.205721, 0, 1

Thank you,

W∴ Balboos, GHB 20-Apr-16 6:23am

Sorry - none of that means anything to me. The names have whatever values and meanings were intended by those who developed the application. I don't even know what your application is doing.

Look up random walk (Wikipedia's a good start) and see if that gives you any ideas based upon what you're doing and what the 'data mining' and such are intended to analyze.