Active Inference for Collective Classification

Authors

  • Mustafa Bilgic University of Maryland at College Park
  • Lise Getoor University of Maryland at College Park

DOI:

https://doi.org/10.1609/aaai.v24i1.7704

Keywords:

active inference, collective classification, statistical relational learning

Abstract

Labeling nodes in a network is an important problem that has seen a growing interest. A number of methods that exploit both local and relational information have been developed for this task. Acquiring the labels for a few nodes at inference time can greatly improve the accuracy, however the question of figuring out which node labels to acquire is challenging. Previous approaches have been based on simple structural properties. Here, we present a novel technique, which we refer to as reflect and correct,that can learn and predict when the underlying classification system is likely to make mistakes and it suggests acquisitions to correct those mistakes.

Downloads

Published

2010-07-05

How to Cite

Bilgic, M., & Getoor, L. (2010). Active Inference for Collective Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 24(1), 1652-1655. https://doi.org/10.1609/aaai.v24i1.7704

Issue

Section

New Scientific and Technical Advances in Research