Fast Inference in Infinite Hidden Relational Models

Relational learning (Dzeroski & Lavrac, 2001; Friedman et al., 1999; Raedt & Kersting, 2003) is an area of growing interest in machine learning. Xu et al. (2006) introduced the infinite hidden relational model (IHRM) which views relational learning in context of the entity-relationship database model with entities, attributes and relations (compare also (Kemp et al., 2006)). In the IHRM, for each entity an auxiliary latent variable is introduced. The latent variable is the only parent of attributes of the entity and is a parent of attributes of relations the entity participates. The number of hidden states is entity class specific. Therefore it is sensible to work with Dirichlet process (DP) mixture models in which each entity class can optimize its own representational complexity in a self-organized way. For our discussion it is sufficient to say that we integrate a DP mixture model into the IHRM by simply letting the number of hidden states for each entity class approach infinity. Thus, a natural outcome of the IHRM is clustering effect providing interesting insight into the structure of the domain.