Scala and Spark code for F3KM: Federated, Fair and Fast k-means.
This code performs 2 distributed algorithms for clustering, using Apache Spark. The implemented algorithms are
- DisBCDKM
- F3KM
For those readers who are not familar with Scala and Spark, we provide a matlab code here.
run driver.scala
When you run this code, it may suffer StackOverFlow error. I suggest you to set RAM with -Xss4m or -Xss8m