Transfer Learning via Relational Type Matching
Authors:
- Raksha KumaraswamyRKRaksha Kumaraswamy
- Phillip OdomPOPhillip Odom
- Kristian KerstingKKKristian Kersting
- David LeakeDLDavid Leake
- Sriraam NatarajanSNSriraam Natarajan
- 1 November 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 811-816
Abstract
Transfer learning is typically performed between problem instances within the same domain. We consider the problem of transferring across domains. To this effect, we adopt a probabilistic logic approach. First, our approach automatically identifies predicates in the target domain that are similar in their relational structure to predicates in the source domain. Second, it transfers the logic rules and learns the parameters of the transferred rules using target data. Finally, it refines the rules as necessary using theory refinement. Our experimental evidence supports that this transfer method finds models as good or better than those found with state-of-the-art methods, with and without transfer, and in a fraction of the time.Keywords
This publication has 10 references indexed in Scilit:
- Learning Markov Logic Networks via Functional Gradient Boosting2011
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009
- Deep transfer via second-order Markov logic2009
- Markov Logic: An Interface Layer for Artificial IntelligenceSynthesis Lectures on Artificial Intelligence and Machine Learning, 2009
- Probabilistic Inductive Logic Programming2008
- Introduction to Statistical Relational Learning2007
- Bayesian Logic Programming: Theory and Tool2007
- Bottom-up learning of Markov logic network structure2007
- Mode Directed Path FindingLecture Notes in Computer Science, 2005
- Adaptive duplicate detection using learnable string similarity measures2003