Details

    Description

      Use some real-life million-size dataset

      Benchmark goals:

      • Index creation time
      • Index update time
      • Index lookup for 1, 10, 100, 1000 entries for the same "query" vector repeated N times.
        • This tests speed of graph lookup with hopefully most data in cache.
      • Index lookup for million different query vectors (top 1, 10, 100, 1000) results, no repetition.
        • This tests speed of graph lookup when data may not all fit in cache.
      • Compute average recall of the algorithm for such queries.

      Compare to papers using the same algorithm.

      Attachments

        Issue Links

          Activity

            Transition Time In Source Status Execution Times
            JiraAutomate made transition -
            In Progress Stalled
            47d 3h 24m 1
            Sergei Golubchik made transition -
            Stalled In Progress
            8m 57s 1
            Sergei Golubchik made transition -
            In Progress Needs Feedback
            25d 5h 4m 1
            Sergei Golubchik made transition -
            Needs Feedback Open
            6s 1
            Sergei Golubchik made transition -
            Open In Progress
            90d 1h 13m 2
            Sergei Golubchik made transition -
            In Progress In Testing
            4s 1
            Sergei Golubchik made transition -
            In Testing Closed
            114d 16h 17m 1

            People

              serg Sergei Golubchik
              serg Sergei Golubchik
              Votes:
              0 Vote for this issue
              Watchers:
              7 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved:

                Git Integration

                  Error rendering 'com.xiplink.jira.git.jira_git_plugin:git-issue-webpanel'. Please contact your Jira administrators.