Labeled Latent Dirichlet Allocation (LLDA) is an extension of the standard unsupervised Latent Dirichlet Allocation (LDA) algorithm, to address multi-label learning tasks. Previous work has shown it to perform in par with other state-ofthe-art multi-label methods. Nonetheless, with increasing label sets sizes LLDA encounters scalability issues. In this work, we introduce Subset LLDA, a simple v...

The one-against-all reduction from multiclass classification to binary classification is a standard technique used to solve multiclass problems with binary classifiers. We show that modifying this technique in order to optimize its error transformation properties results in a superior technique, both experimentally and theoretically. This algorithm can also be used to solve a more general class...

Multi-label classification is a challenging and appealing supervised learning problem where a subset of labels, rather than a single label seen in traditional classification problems, is assigned to a single test instance. Classifier chains based methods are a promising strategy to tackle multi-label classification problems as they model label correlations at acceptable complexity. However, the...

A formalism is proposed for representing uncertain information on set-valued variables using the formalism of belief functions. A set-valued variableX on a domain Ω is a variable taking zero, one or several values in Ω. While defining mass functions on the frame 22 Ω is usually not feasible because of the double-exponential complexity involved, we propose an approach based on a definition of a ...

Many hierarchical multi-label classification systems predict a real valued score for every (instance, class) couple, with a higher score reflecting more confidence that the instance belongs to that class. These classifiers leave the conversion of these scores to an actual label set to the user, who applies a cut-off value to the scores. The predictive performance of these classifiers is usually...

0167-8655/$ see front matter 2013 Elsevier B.V. All rights reserved. http://dx.doi.org/10.1016/j.patrec.2013.10.016 ⇑ Corresponding author. Tel.: +389 2 3099 159. E-mail addresses: [email protected] (I. Dimitrovski), Dragi. [email protected] (D. Kocev), [email protected] (S. Loskovska), Saso. [email protected] (S. Džeroski). Ivica Dimitrovski a,⇑, Dragi Kocev , Suzana Losko...

In this supplement, we provide details on the multi-label model and also prove some of the theoretical results in the main paper. Let L be the set of all labels that a node can take. We will denote labels a ∈ L by fractional characters. The multi-label extension of the directed cooperative cut energy that is defined in the main paper is

Investigating subjective values of audio data is both interesting and pleasant topic for research, gaining attention and popularity among researchers recently. We focus on automatic detection of emotions in songs/audio files, using features based on spectral contents. The data set, containing a few hundreds of music pieces, was used in experiments. The emotions are grouped into 13 or 6 classes....

In Figure 1 we show an example of the need to collect the multi-label ML-CUFED dataset with because of albums with ambiguous or multiple event types. The two albums in Figure 1 are both labeled as birthday events in CUFED, but they can also fall into the category of casual family/friends gathering. These two event types are not mutually exclusive. Moreover, intuitively, we would consider the al...

We consider multi-label classification problems in application scenarios where classifier accu-racy is not satisfactory, but manual annotation is too costly. In single-label problems, a wellknown solution consists of using a reject option, i.e., allowing a classifier to withhold unreliabledecisions, leaving them (and only them) to human operators. We argue that this solution can be<...