AAAI Publications, Sixteenth International Conference on Principles of Knowledge Representation and Reasoning

Font Size: 
Structure Learning for Relational Logistic Regression:An Ensemble Approach
Nandini Ramanan, Gautam Kunapuli, Tushar Khot, Bahare Fatemi, Seyed Mehran Kazemi, David Poole, Kristian Kersting, Sriraam Natarajan

Last modified: 2018-09-24

Abstract


We consider the problem of learning Relational Logistic Regression (RLR). Unlike standard logistic regression, the features of RLRs are first-order formulae with associated weight vectors instead of scalar weights. We turn the problem of learning RLR to learning these vector-weighted formulae and develop a learning algorithm based on functional-gradient boosting methods for probabilistic logic models. Our empirical evaluation on standard data sets demonstrates the superiority of our approach over other methods for learning RLR.

Keywords


Probabilistic graphical models; Learning; Relational

Full Text: PDF