Sample-Based Attribute Selective A$n$ DE for Large Data
- 13 September 2016
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 29 (1) , 172-185
Abstract
More and more applications have come with large data sets in the past decade. However, existing algorithms cannot guarantee to scale well on large data. Averaged n-Dependence Estimators (AnDE) allows for flexible learning from out-of-core data, by varying the value of n (number of super parents). Hence, AnDE is especially appropriate for large data learning. In this paper, we propose a sample-based attribute selection technique for AnDE. It needs one more pass through the training data, in which a multitude of approximate AnDE models are built and efficiently assessed by leave-one-out cross validation. The use of a sample reduces the training time. Experiments on 15 large data sets demonstrate that the proposed technique significantly reduces AnDE's error at the cost of a modest increase in training time. This efficient and scalable out-of-core approach delivers superior or comparable performance to typical in-core Bayesian network classifiers.Keywords
Funding Information
- Australian Research Council (DP140100087)
- Asian Office of Aerospace Research and Development
- Air Force Office of Scientific Research (FA2386-15-1-4007)
- National Natural Science Foundation of China (61202135)
- Natural Science Foundation of Jiangsu (BK20130735)
- Natural Science Foundation of Jiangsu Higher Education Institutions of China (14KJB520019, 13KJB520011, 13KJB520013)
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education
- Development of Jiangsu Higher Education Institutions
- Monash e-Research Center and eSolutions-Research
- HPC
- LIEF
- NCI National Facility in Canberra
- Australian Commonwealth Government
This publication has 31 references indexed in Scilit:
- Selective AnDE for large data learning: a low-bias memory constrained approachKnowledge and Information Systems, 2016
- Highly Scalable Attribute Selection for Averaged One-Dependence Estimators2014
- Creating and benchmarking a new dataset for physical activity monitoring2012
- An Agent-Based Approach to Care in Independent Living2010
- The Elements of Statistical Learning2009
- Random ForestsMachine Learning, 2001
- Bayesian Network ClassifiersMachine Learning, 1997
- The power of decision tables1995
- Induction of Selective Bayesian Classifiers1994
- Approximating discrete probability distributions with dependence treesIEEE Transactions on Information Theory, 1968