[
https://issues.apache.org/jira/browse/FLINK-3879?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15275160#comment-15275160
]
GaoLun commented on FLINK-3879:
-------------------------------
Hi [~greghogan], the PR of FLINK-2044 has been updated and support returning
both value now. And i have changed the normalization method from sum to square
sum.
I wrote a simple test for your implementation to compare the result with mine,
but i find the result is different.
For a simple graph: {{1->2, 1->3, 2->3}} with one iteration
result :
Mine: {{(1,0.8320502943378436,0.0), (2,0.554700196225229,0.4472135954999579),
(3,0.0,0.8944271909999159)}}
Yours: {{(1,0.8320502943378437,0.0), (2,0.5547001962252291,0.5144957554275265),
(3,0.0,0.8574929257125441)}}
We can calculate the hub/authority value manually, the result should be:
{{(1, sqrt(9/13), 0.0), (2,sqrt(4/13), 1/sqrt(5)), (3, 0.0, 2/sqrt(5))}}
which is a little different with yours.
> Native implementation of HITS algorithm
> ---------------------------------------
>
> Key: FLINK-3879
> URL: https://issues.apache.org/jira/browse/FLINK-3879
> Project: Flink
> Issue Type: New Feature
> Components: Gelly
> Affects Versions: 1.1.0
> Reporter: Greg Hogan
> Assignee: Greg Hogan
> Fix For: 1.1.0
>
>
> Hyperlink-Induced Topic Search (HITS, also "hubs and authorities") is
> presented in [0] and described in [1].
> "[HITS] is a very popular and effective algorithm to rank documents based on
> the link information among a set of documents. The algorithm presumes that a
> good hub is a document that points to many others, and a good authority is a
> document that many documents point to."
> [https://pdfs.semanticscholar.org/a8d7/c7a4c53a9102c4239356f9072ec62ca5e62f.pdf]
> This implementation differs from FLINK-2044 by providing for convergence,
> outputting both hub and authority scores, and completing in half the number
> of iterations.
> [0] http://www.cs.cornell.edu/home/kleinber/auth.pdf
> [1] https://en.wikipedia.org/wiki/HITS_algorithm
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
