Distributed Knowledge Discovery with the Parallel KDDML System

A. Romei, M. Sciolla, F. Turini, and M. Valentini (Italy)

Keywords

Distribuited knowledge discovery, privacy preserving, data immovability.

Abstract

KDDML is a middleware language and system for knowl edge discovery. The challenge that motivated the devel opment of a distributed version of the originally “stand alone” KDDML (KDD Markup Language) environment was on one side to exploit the parallelism, and on the other side to overcome the problem of data immovability, a quite frequent restriction on real-world data collections that has principally a privacy-preserving purpose. The last question is addressed by moving the code and “mining” the data “on the place”, that is by adapting the computation to the avail ability and localization of the data.

Important Links:



Go Back