[jira] [Commented] (SPARK-3066) Support recommendAll in matrix factorization model

["Debasish Das (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SPARK-3066?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14389973#comment-14389973 ] 

Debasish Das commented on SPARK-3066:
-------------------------------------

Also unless the raw flow runs there is no way to validate how good a LSH based flow is doing since users...I updated the PR today with [~mengxr] reviews...I am working on level 3 BLAS routines for item->item similarity calculation from matrix factors and the same optimization can be applied here...I will open up the PR for that in coming weeks...we already have a JIRA for rowSimilarities...

> Support recommendAll in matrix factorization model
> --------------------------------------------------
>
>                 Key: SPARK-3066
>                 URL: https://issues.apache.org/jira/browse/SPARK-3066
>             Project: Spark
>          Issue Type: New Feature
>          Components: MLlib
>            Reporter: Xiangrui Meng
>            Assignee: Debasish Das
>
> ALS returns a matrix factorization model, which we can use to predict ratings for individual queries as well as small batches. In practice, users may want to compute top-k recommendations offline for all users. It is very expensive but a common problem. We can do some optimization like
> 1) collect one side (either user or product) and broadcast it as a matrix
> 2) use level-3 BLAS to compute inner products
> 3) use Utils.takeOrdered to find top-k



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org