Github user gaborhermann commented on a diff in the pull request:

    https://github.com/apache/flink/pull/2542#discussion_r87354805
  
    --- Diff: 
flink-libraries/flink-ml/src/main/scala/org/apache/flink/ml/recommendation/ALS.scala
 ---
    @@ -535,8 +581,17 @@ object ALS {
         itemOut: DataSet[(Int, OutBlockInformation)],
         userIn: DataSet[(Int, InBlockInformation)],
         factors: Int,
    -    lambda: Double, blockIDPartitioner: FlinkPartitioner[Int]):
    +    lambda: Double, blockIDPartitioner: FlinkPartitioner[Int],
    +    implicitPrefs: Boolean,
    +    alpha: Double):
       DataSet[(Int, Array[Array[Double]])] = {
    +    // retrieve broadcast XtX matrix in implicit case
    +    val XtXtoBroadcast = if (implicitPrefs) {
    --- End diff --
    
    I tried to fit the notation of the explicit ALS code, as it uses `userXtX` 
notation in the `updateFactors` function. I think it might be confusing to use 
two different notations is the code, even if the paper uses another notation.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

Reply via email to