2003 LinkPredictionInRelData

From GM-RKB
(Redirected from Taskar et al. 2003)
Jump to navigation Jump to search

Subject Heading: Link Prediction Task, Link Prediction Algorithm

Notes

Cited by

Quotes

Abstract

Many real-world domains are relational in nature, consisting of an set of objects related to each other in complex ways. This paper focuses on predicting the existence and the type of links between entities in such domains. We apply the relational Markov network framework of Taskar et al. to define a joint probabilistic model over the entire link graphentity attributes and links. The application of the RMN algorithm to this task requires the definition of probabilistic patterns over subgraph structures. We apply this method to two new relational datasets, one involving university webpages, and the other a social network. We show that the collective classification approach of RMNs, and the introduction of subgraph patterns over link labels, provide significant improvements in accuracy over flat classification, which attempts to predict each link in isolation.


References


,

 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2003 LinkPredictionInRelDataDaphne Koller
Pieter Abbeel
Ming-Fai Wong
Ben Taskar
Link Prediction in Relational DataNeural Information Processing Systems Conferencehttp://www.seas.upenn.edu/~taskar/pubs/link.pdf2003