An extensive experimental comparison of methods for multi-label learning

By Gjorgji Madjarov, Dragi Kocev, Dejan Gjorgjevikj, Saso Dzeroski. 2012

761 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Molecular Biology

Citations in the corpus

Datasheet for the Pile (2022, methodology): “Enron Emails: The Enron Emails have been used extensively, including by [Diesner et al., 2005, Kossinets et al., 2008, Tang et al., 2008, Crammer et al., 2009, Madjarov et al., 2012].”
Lift: Multi-Label Learning with Label-Specific Features (2011, background): “Few notable exceptions are [30] and [38] where a total of 11 and 15 data sets have been considered respectively.”
Multi-Label Learning with Global and Local Label Correlation (2017, background): “An extensive experimental study on various approaches can be found in [26].”
A survey on multi‐output regression (2015, background): “When the output variables are binary, the learning problem is called multi-label classiﬁcation 11–13 .”
A Tutorial on Multilabel Learning (2015, methodology): “1984] of the variables from the target tuple, and the prototype function returns a vector with probabilities for each label [Madjarov et al. 2012].”
A Review on Multi-Label Learning Algorithms (2014, background): “A recent attempt towards extensive experimental comparison can be found in [103] where 12 multi-label learning algorithms are compared with respect to 16 evaluation metrics.”
Learning shared subspace for multi-label dimensionality reduction via dependence maximization (2015, methodology): “Detailed description of these criteria can be found in [21].”
Addressing imbalance in multilabel classification: Measures and random resampling algorithms (2015, background): “As stated in [39], it is important to use several of them to assess predictive performance.”
Multi-target regression via input space expansion: treating targets as inputs (2012, neutral): “It is interesting to note that the predictive clustering framework is an example of a technique that originally focused on multi-target regression, and only recently showcased its effectiveness on multi-label classification (Vens et al., 2008; Madjarov et al., 2012).”
Gated Multimodal Units for Information Fusion (2017, methodology): “Concretely, we calculate them as follows (Madjarov et al., 2012): With N the number of examples; Q the number of labels; Q j the number of true instances for the j -th label; p the precision, r the recall; ˆ y i , y i ∈ (0 , 1) Q the prediction and ground truth binary tuples respectively; tp j , fp…”