Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-14371

OnlineLDAOptimizer should not collect stats for each doc in mini-batch to driver

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • None
    • 2.3.0
    • MLlib
    • None

    Description

      See this line: https://github.com/apache/spark/blob/5743c6476dbef50852b7f9873112a2d299966ebd/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAOptimizer.scala#L437

      The second element in each row of "stats" is a list with one Vector for each document in the mini-batch. Those are collected to the driver in this line:
      https://github.com/apache/spark/blob/5743c6476dbef50852b7f9873112a2d299966ebd/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAOptimizer.scala#L456

      We should not collect those to the driver. Rather, we should do the necessary maps and aggregations in a distributed manner. This will involve modify the Dirichlet expectation implementation. (This JIRA should be done by someone knowledge about online LDA and Spark.)

      Attachments

        Issue Links

          Activity

            People

              acopich Valeriy Avanesov
              josephkb Joseph K. Bradley
              Joseph K. Bradley Joseph K. Bradley
              Votes:
              0 Vote for this issue
              Watchers:
              6 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: