Esther Galbrun is a doctoral student at the University of Helsinki and Helsinki Institute for Information Technology (HIIT), Finland. Her research is centered on the data mining problem of finding redescriptions.
We introduce relational redescription mining, that is, the task of
finding two structurally different patterns that describe nearly the
same set of object tuples in a relational dataset. By extending
redescription mining beyond propositional and real-valued attributes,
it provides a powerful tool to match different relational descriptions
of the same concept.
We propose an alternating scheme for solving this problem. Its core
consists of a relational query miner that efficiently identifies
discriminative connection patterns between pairs of nodes.
We compare our proposed query miner to a baseline ILP approach and
present examples of redescriptions found from the UMLS, UW-CSE and
Kinship relational datasets.