Performance controlled data reduction for knowledge discovery in distributed databases

The objective of data reduction is to obtain a compact representation of a large data set to facilitate repeated use of non-redundant information with complex and slow learning algorithms and to allow efficient data transfer and storage. For a user-controllable allowed accuracy loss we propose an effective data reduction procedure based on guided sampling for identifying a minimal size representative subset, followed by a model-sensitivity analysis for determining an appropriate compression level for each attribute. Experiments were performed on 3 large data sets and, depending on an allowed accuracy loss margin ranging from 1% to 5% of the ideal generalization, the achieved compression rates ranged between 95 and 12,500 times. These results indicate that transferring reduced data sets from multiple locations to a centralized site for an efficient and accurate knowledge discovery might often be possible in practice.