Sharing learned models among remote database partitions by local meta-learning

Proposed meta-learning strategies in previous work are extended to integrate local and remote models to improve models learned over locally available data sources to learn more accurate knowledge from globally available data.

Abstract

We explore the possibility of importing “black-box ” models learned over data sources at remote sites to improve models learned over locally avail-able data sources. In this way, we may be able to learn more accurate knowledge from globally available data than would otherwise be possible from partial, locally available data. Proposed meta-learning strategies in our previous work are extended to integrate local and remote models. We also investigate the effect on accuracy perfor-mance when data overlap among different sites.