Finding the Right Family: Parent and Child Selection for Averaged One-Dependence Estimators

Zheng, Fei; Webb, Geoffrey I.

doi:10.1007/978-3-540-74958-5_45

Cited by 11 publications

(17 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because attributes play multiple roles, either parent or child, in an AODE model, there are four types of attribute elimination for AODE (Zheng and Webb 2007). To formalize the various attribute elimination strategies we introduce into AODE the use of a parent (p) and a child (c) set, each of which contains the set of indices of attributes that can be employed in respectively a parent or child role in AODE.…”

Section: Aode With Bsementioning

confidence: 99%

Subsumption resolution: an efficient and effective technique for semi-naive Bayesian learning

et al. 2011

Self Cite

View full text Add to dashboard Cite

Semi-naive Bayesian techniques seek to improve the accuracy of naive Bayes (NB) by relaxing the attribute independence assumption. We present a new type of seminaive Bayesian operation, Subsumption Resolution (SR), which efficiently identifies occurrences of the specialization-generalization relationship and eliminates generalizations at classification time. We extend SR to Near-Subsumption Resolution (NSR) to delete neargeneralizations in addition to generalizations. We develop two versions of SR: one that performs SR during training, called eager SR (ESR), and another that performs SR during testing, called lazy SR (LSR). We investigate the effect of ESR, LSR, NSR and conventional attribute elimination (BSE) on NB and Averaged One-Dependence Estimators (AODE), a powerful alternative to NB. BSE imposes very high training time overheads on NB and AODE accompanied by varying decreases in classification time overheads. ESR, LSR and NSR impose high training time and test time overheads on NB. However, LSR imposes no extra training time overheads and only modest test time overheads on AODE, while ESR and NSR impose modest training and test time overheads on AODE. Our extensive experimental comparison on sixty UCI data sets shows that applying BSE, LSR or NSR to NB significantly improves both zero-one loss and RMSE, while applying BSE, ESR or NSR to AODE significantly improves zero-one loss and RMSE and applying LSR to AODE significantly improves zero-one loss. The Friedman test and Nemenyi test show that AODE with ESR or NSR have a significant zero-one loss and RMSE advantage over Logistic Regression and a zero-one loss advantage over Weka's LibSVM implementation with a grid parameter search on categorical data. AODE with LSR has a zero-one loss advantage over Logistic Regression and comparable zero-one loss with LibSVM. Finally, we examine the circumstances under which the elimination of near-generalizations proves beneficial.

show abstract

Section: Aode With Bsementioning

confidence: 99%

Subsumption resolution: an efficient and effective technique for semi-naive Bayesian learning

et al. 2011

Self Cite

View full text Add to dashboard Cite

show abstract

“…Representative examples include TAN and SP-TAN [12], [18], AODE and its variants [29], [34], [35], [31], HNB [32], etc. TAN restricts that each attribute can only depend on one parent in addition to the class, and thus it follows that…”

Section: Background and Related Workmentioning

confidence: 99%

Semi-naive Exploitation of One-Dependence Estimators

Zhou

2009

2009 Ninth IEEE International Conference on Data Mining

View full text Add to dashboard Cite

Abstract-It is well known that the key of Bayesian classifier learning is to balance the two important issues, that is, the exploration of attribute dependencies in high orders for ensuring a sufficient flexibility in approximating the ground-truth dependencies, and the exploration of low orders for ensuring a stable probability estimate from limited training samples. By allowing one-order attribute dependencies, one-dependence estimators (ODEs) have been shown to be able to approximate the ground-truth attribute dependencies whilst keeping the effectiveness of probability estimation, and therefore leading to excellent performance. In previous studies, however, ODEs were exploited in simple ways, such as by averaging, for classification. In this paper, we propose a semi-naive exploitation of ODEs that fits a function of ODEs to pursue higher-order attribute dependencies. Extensive experiments show that the proposed SNODE approach can achieve better performance than many state-of-the-art Bayesian classifiers.

show abstract

“…As indicated in [5], the performance of BSE is better than FSS, so we focus on BSE in this paper. Four types of attribute elimination are considered, parent elimination (PE), child elimination (CE), parent and child elimination (P∧CE), parent or child elimination (P∨CE) which performs the former three types of attribute eliminations in each iteration, selecting the option that best reduces the error.…”

Section: Forward and Backward Attribute Selection In Aodementioning

confidence: 99%

“…In order to repair harmful inter-dependencies among highly correlated attributes, Zheng et al [5] proposed to select an appropriate attribute subset by hill climbing search. Two different search strategies can be used: FSS begins with the empty attribute set and successively adds attributes [10], while BSE starts with the complete attribute set and successively removes attributes [11].…”

Section: Forward and Backward Attribute Selection In Aodementioning

confidence: 99%

See 1 more Smart Citation

Highly Scalable Attribute Selection for Averaged One-Dependence Estimators

Chen

Martínez

Webb

2014

Advances in Knowledge Discovery and Data Mining

Self Cite

View full text Add to dashboard Cite

Abstract. Averaged One-Dependence Estimators (AODE) is a popular and effective approach to Bayesian learning. In this paper, a new attribute selection approach is proposed for AODE. It can search in a large model space, while it requires only a single extra pass through the training data, resulting in a computationally efficient two-pass learning algorithm. The experimental results indicate that the new technique significantly reduces AODE's bias at the cost of a modest increase in training time. Its low bias and computational efficiency make it an attractive algorithm for learning from big data.

show abstract

Finding the Right Family: Parent and Child Selection for Averaged One-Dependence Estimators

Cited by 11 publications

References 15 publications

Subsumption resolution: an efficient and effective technique for semi-naive Bayesian learning

Subsumption resolution: an efficient and effective technique for semi-naive Bayesian learning

Semi-naive Exploitation of One-Dependence Estimators

Highly Scalable Attribute Selection for Averaged One-Dependence Estimators

Contact Info

Product

Resources

About