Exploiting Label Interdependencies in Multi-label Classification

Glinka, Kinga; Wosiak, Agnieszka; Zakrzewska, Danuta

doi:10.1007/978-3-030-19738-4_7

Cited by 1 publication

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where h is a function that predicts a labeling based on the distribution of labels. The task of risk minimization is finding h * that minimizes (7). Clearly this can be achieved by exhaustive search (testing all 2 n possible labelings), but the minimum should be obtained efficiently (in polynomial time, if possible).…”

Section: Probabilistic Frameworkmentioning

confidence: 99%

“…The idea of many published transformation-based MLC methods is improving performance by exploiting dependencies among labels. [2][3][4][5][6][7] Generally, the study of dependence among labels may consider the impacts of different types of dependence, the "strength" of the dependence, how to use the dependence to achieve better performance and how to capture dependence.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An experimental framework for evaluating loss minimization in multi‐label classification via stochastic process

Mello

Varejão

Rodrigues

2021

Computational Intelligence

View full text Add to dashboard Cite

One major challenge multi‐label classification faces, are the conditions for evaluating multi‐label algorithms. Simplistic experimental setups based on artificial data may not capture crucial situations for analyzing these algorithms. This article introduces an experimental framework for evaluating multi‐label algorithms by artificially generating the probabilistic label distributions. The proposed framework has the benefits of considering a wide variety of labels distributions, and enables users to simulate probability label distributions with a better control of the label dependence and the difficulty of the problem. An experimental study was conducted using the framework where new findings with respect to five methods, binary relevance, classifier chain, dependent binary relevance, calibrated label ranking by pairwise comparison and probabilistic classifier chain, were revealed. This framework will facilitate conducting new experimental studies for analysing the effects of changing label dependence and the difficulty of the problem on the performance of new multi‐label algorithms.

show abstract

Section: Probabilistic Frameworkmentioning

confidence: 99%