Meta-Prediction for Collective Classification

Abstract

When data instances are inter-related, as are nodes in a social network or hyperlink graph, algorithms for collective classification (CC) can significantly improve accuracy. Recently, an algorithm for CC named Cautious ICA (ICAC) was shown to improve accuracy compared to the popular ICA algorithm. ICAC improves performance by initially favoring its more confident predictions during collective inference. In this paper, we introduce ICAMC, a new algorithm that outperforms ICAC when the attributes that describe each node are not highly predictive. ICAMC learns a meta-classifier that identifies which node label predictions are most likely to be correct. We show that this approach significantly increases accuracy on a range of real and synthetic data sets. We also describe new features for the meta-classifier and demonstrate that a simple search can identify an effective feature set that increases accuracy.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2010
Accession Number
ADA553104

Entities

People

  • David W. Aha
  • Kalyan M. Gupta
  • Luke K. Mcdowell

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Artificial Intelligence
  • Classification
  • Computer Science
  • Data Mining
  • Data Science
  • Data Sets
  • Information Science
  • Machine Learning
  • Network Science
  • Probabilistic Models
  • Probability
  • Social Networks
  • Test Sets
  • Training

Fields of Study

  • Computer science

Readers

  • Applied Combinatorial Optimization and Logic Circuit Design.
  • Theoretical Analysis.
  • Urban Planning and Geography.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks