Evaluating MLNs for Collective Classification
Abstract
Collective Classification is the process of labeling instances in a graph using both instance attribute information and information about relations between instances. While several Collective Classification Algorithms have been well studied, the use of Markov Logic Networks (MLNs) remains largely untested. MLNs pair first order logic statements with a numerical weight. With properly assigned weights, these rules may be used to infer class labels from evidence stated as logic statements. Our study evaluated MLNs against other Collective Classification algorithms on both synthetic data and real date from the CiteSeer dataset. Also whole, we encountered inconsistent and often poor performance with MLNs, especially on synthetic data where other Collective Classification algorithms performed well.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 13, 2010
- Accession Number
- ADA535643
Entities
People
- Robert J. Crane