Hulten, G., & Domingos, P. (2002). Mining complex models from arbitrarily large databases in constant time. ACM SIGKDD 8. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
A General Framework for Mining Massive Data Stream - Domingos, Hulten (2003) Self-citation (Hulten Domingos) (Correct)
No context found.
G. Hulten and P. Domingos. Mining complex models from arbitrarily large databases in constant time. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 525--531, Edmonton, Canada, 2002. ACM Press.
Mining Massive Relational Databases - Hulten, Domingos, Abe Self-citation (Hulten Domingos) (Correct)
....settings. Another class of scaling challenges comes from the nature of the processes that generate large data sets. These processes exist over long periods of time and continuously generate data, and the distribution of this data often changes drastically as time goes by. In previous work [Hulten and Domingos, 2002] we developed a framework capable of semi automatically scaling up a wide class of propositional learning algorithms to address all of these challenges simultaneously. In the remainder of this paper we begin to extend our propositional scaling framework to the challenge of learning from massive ....
....example. In our context, this means that the entire data set needs to be flattened before feature selection can take place, which results in no speed gain. If we are willing to accept a small chance of making an error, we can use sampling to do much better. VFREL uses techniques developed by Hulten and Domingos [2002] and others to do just that. Standard statistical results can be used to obtain a high confidence bound on the difference between the gain observed for a feature on a sample of data and the true gain of the feature. For example, the Hoeffding bound [Hoeffding, 1963] says the following. Let a ....
G. Hulten and P. Domingos. Mining complex models from arbitrarily large databases in constant time. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 525-- 531, Edmonton, Canada, 2002. ACM Press.
Research on Statistical Relational Learning at the University of .. - Domingos (2003) Self-citation (Hulten Domingos) (Correct)
....in computing an aggregate (e.g. sum, average, count) again ensuring that the result is not significantly different from what we would obtain using all the relevant tuples. This is based on our previous work in applying subsampling techniques to propositional learners [Domingos and Hulten, 2000; Hulten and Domingos, 2002] Beyond this, we envisage that intelligent control of which tuples a learner looks at, and which join paths it pursues, will be key to scalable SRL. Heuristics for this are thus an important area of research. 6 Knowledge Integration In traditional learning, data must first be gathered, ....
G. Hulten and P. Domingos. Mining complex models from arbitrarily large databases in constant time. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 525--531, Edmonton, Canada, 2002. ACM Press.
Learning Bayesian Networks From Dependency Networks: A .. - Hulten, Chickering.. (2003) Self-citation (Hulten) (Correct)
No context found.
G. Hulten and P. Domingos. Mining complex models from arbitrarily large databases in constant time. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 525--531, Edmonton, Alberta, Canada, 2002. ACM Press.
Tractable Learning of Large Bayes Net Structures from Sparse.. - Anna Goldenberg Anya (Correct)
No context found.
Hulten, G., & Domingos, P. (2002). Mining complex models from arbitrarily large databases in constant time. ACM SIGKDD 8.
Learning in First-Order Probabilistic Representations - Matthew Richardson Ph (2003) (Correct)
No context found.
G. Hulten and P. Domingos (2002). Mining complex models from arbitrarily large databases in constant time. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, to appear.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC