Incorporating label dependency into the binary relevance framework for multi-label classification

Alvares-Cherman, Everton; Metz, Jean; Monard, Maria Carolina

doi:10.1016/j.eswa.2011.06.056

Cited by 72 publications

(28 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The approach has been shown to be very competitive [10]. Despite its successes [29], however, BR has also been criticized for the label-independence assumption [5], [10], [11], [12], [15], [16], [21]; and it is also known to suffer from imbalanced class representation in the binary training sets. The latter issue was discussed at great length in [30] and [31].…”

Section: Problem Transformation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

PruDent: A Pruned and Confident Stacking Approach for Multi-Label Classification

Al‐Ali

Kubát

2015

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Over the past decade or so, several research groups have addressed the problem of multi-label classification where each example can belong to more than one class at the same time. A common approach, called Binary Relevance (BR), addresses this problem by inducing a separate classifier for each class. Research has shown that this framework can be improved if mutual class dependence is exploited: an example that belongs to class X is likely to belong also to class Y ; conversely, belonging to X can make an example less likely to belong to Z. Several works sought to model this information by using the vector of class labels as additional example attributes. To fill the unknown values of these attributes during prediction, existing methods resort to using outputs of other classifiers, and this makes them prone to errors. This is where our paper wants to contribute. We identified two potential ways to prune unnecessary dependencies and to reduce error-propagation in our new classifier-stacking technique, which is named PruDent.Experimental results indicate that the classification performance of PruDent compares favorably with that of other state-of-the-art approaches over a broad range of testbeds. Moreover, its computational costs grow only linearly in the number of classes.

show abstract

Section: Problem Transformation Methodsmentioning

confidence: 99%

“…Typically, they rely on extending the attribute vectors by information about the classes to which the given example has already been shown to belong [3], [10], [12], [13], [14], [15], [16]. In our opinion, though, most of these papers fail to pay adequate attention to two critical issues: error-propagation, and unnecessary relationships.…”

Section: Introductionmentioning

confidence: 98%

PruDent: A Pruned and Confident Stacking Approach for Multi-Label Classification

Al‐Ali

Kubát

2015

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…The rationale is to avoid additional noise that is introduced from completely uncorrelated labels. BR+ is another approach similar to Meta-Stacking (Alvares-Cherman et al [1]) that uses not all the label information at the meta level, but excludes the label being predicted itself. Additionally, it updates the label information at the meta level in a manner that is similar to CC using different chains.…”

Section: Related Workmentioning

confidence: 99%

On the spectrum between binary relevance and classifier chains in multi-label classification

Burkhardt¹,

Krämer²

2015

Proceedings of the 30th Annual ACM Symposium on Applied Computing

View full text Add to dashboard Cite

Two fundamental and prominent methods for multi-label classification, Binary Relevance (BR) and Classifier Chains (CC), are usually considered to be distinct methods without direct relationship. However, BR and CC can be generalized to one single method: blockwise classifier chains (BCC), where labels within a block (i.e. a group of labels of fixed size) are predicted independently as in BR but then combined to predict the next block's labels as in CC. In other words, only the blocks are connected in a chain. BR is then a special case of BCC with a block size equal to the number of labels, and CC a special case with a block size equal to one. The rationale behind BCC is to limit the propagation of errors made by inaccurate classifiers early in the chain, which should be alleviated by the expected block effect. Another, yet different generalization is based on the divideand-conquer principle, not error propagation, but fails to exhibit the desired block effect. Ensembles of BCC are also discussed and experiments confirm that their performance is on par with ensembles of CC. Further experiments show the effect of the block size, in particular with respect to the performance of the two extremes, BR and CC. As it turns out, some regions of the block size parameter space lead to degraded performance, whereas others improve performance to a noticeable but modest extent.

show abstract

“…Behaviour segmentation is based on a deep understanding of the customer's current behaviour data, which mainly research past and current consumer behaviour and mode through the enterprise database (Alvares-Cherman et al, 2012). The purpose is to predict the future behaviour of customers, and develop targeted strategies to meet customer needs by customer classification.…”

Section: Customer Behaviour Segmentationmentioning

confidence: 99%

Research on financial advertisement personalised recommendation method based on customer segmentation

Wang

Liu

Wu³

2018

IJWMC

View full text Add to dashboard Cite

Incorporating label dependency into the binary relevance framework for multi-label classification

Cited by 72 publications

References 9 publications

PruDent: A Pruned and Confident Stacking Approach for Multi-Label Classification

PruDent: A Pruned and Confident Stacking Approach for Multi-Label Classification

On the spectrum between binary relevance and classifier chains in multi-label classification

Research on financial advertisement personalised recommendation method based on customer segmentation

Contact Info

Product

Resources

About