Lise Getoor
ABSTRACT
Machine learning and database approaches to structured probabilistic models share many commonalities, yet exhibit certain important differences. Machine learning methods focus on learning probabilistic models from (certain) data and efficient learning and inference, whereas probabilistic database approaches focus on storing and efficiently querying uncertain data. Nonetheless, the structured probabilistic models that both use are often (almost) identical. In this tutorial, I will overview the field of statistical relational learning (SRL) [1] and survey common approaches. I'll make connections to work in probabilistic databases [2], and highlight commonalities and differences among them. I'll close by describing some of our recent work on probabilistic soft logic [3].
- Getoor, L., and Taskar, B. 2007. Introduction to Statistical Relational Learning. MIT Press. Google Scholar
Digital Library
- Suciu, D, Olteanu, D, Ré, C., and Koch, C. 2011. Probabilistic Databases. Synthesis Lectures on Data Management. Morgan & Claypool Publishers. Google ScholarDigital Library
- Bach, S, Broecheler, M., Huang, B, and Getoor, L. 2015. Hinge-Loss Markov Random Fields and Probabilistic Soft Logic. ArXiv:1505.04406 {cs.LG}Google Scholar
Index Terms
- Statistical Relational Learning: Unifying AI & DB Perspectives on Structured Probabilistic Models
Recommendations
Learning statistical models from relational data
SIGMOD '11: Proceedings of the 2011 ACM SIGMOD International Conference on Management of dataStatistical Relational Learning (SRL) is a subarea of machine learning which combines elements from statistical and probabilistic modeling with languages which support structured data representations. In this survey, we will: 1) provide an introduction ...
An inductive logic programming approach to statistical relational learning: Thesis
Statistical relational learning (SRL) addresses one of the central open questions of AI: the combination of relational or first-order logic with principled probabilistic and statistical approaches to inference and learning. This thesis approaches SRL ...
A relational database model and algebra integrating fuzzy attributes and probabilistic tuples
AbstractAlthough there have been many fuzzy or probabilistic relational database models proposed for representing and handling imprecise and uncertain information of objects in real-world applications, models combining the relevance and ...
Comments