[
https://issues.apache.org/jira/browse/MADLIB-1084?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16418293#comment-16418293
]
Jingyi Mei commented on MADLIB-1084:
------------------------------------
[~fmcquillan]
Concerning the name of the parameters, here is what I found:
In many stanford Personalized PageRank Project related papers, they use a term
`Personalized Pagerank Vector(PPV)`
[http://ilpubs.stanford.edu:8090/530/1/2002-12.pdf]
or ` personalization vector` [http://ilpubs.stanford.edu:8090/596/1/2003-35.pdf]
since mathematically, a vector is used to calculate personalized pagerank score.
This might be the incentive that NetworkX uses "personalization" as the
parameter name and "The personalization vector consisting of a dictionary with
a key for every graph node and nonzero personalization value for each node" as
explanation.
Meanwhile, there is some other paper that uses "nodes of interests" to refer
those special nodes with personalized value in the Personalized Pagerank Vector
[http://ieeexplore.ieee.org/document/8048459/?reload=true]
In many research, they use webpage and different users as subject, and bookmark
is used as an example of special nodes. In this context, "nodes of interests"
makes it more vivid.
For Oracle PGX implementation, they just name it "source", which is "the set of
chosen nodes from the graph for personalization".
Personally, I prefer a name with the word "personalization" in it -
"nodes_of_personalization" ,"personalization_nodes", etc. But
"nodes_of_interest" can also convey good msg, especially in a internet-and-user
context.
> Graph - Personalized PageRank
> -----------------------------
>
> Key: MADLIB-1084
> URL: https://issues.apache.org/jira/browse/MADLIB-1084
> Project: Apache MADlib
> Issue Type: New Feature
> Components: Module: Graph
> Reporter: Frank McQuillan
> Assignee: Himanshu Pandey
> Priority: Major
> Fix For: v1.14
>
>
> Personalized PageRank which is a variant of regular PageRank.
> Please refer to
> [http://madlib.apache.org/docs/latest/group__grp__pagerank.html] as a
> starting point.
> Reference:
> Neighborhood Formation and Anomaly Detection in Bipartite Graphs
> [http://www.cs.cmu.edu/~deepay/mywww/papers/icdm05.pdf]
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
