Structuring the Output Space in Multi-label Classification by Using Feature Ranking

Nikoloski, Stevanche; Kocev, Dragi; Džeroski, Sašo

doi:10.1007/978-3-319-78680-3_11

Cited by 4 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The difference here with single PCTs is Generally, on the larger datasets, there is an improvement of the performance, when the hierarchies are used. More precisely, divisive methods for clustering (hierarchy creation) are the best methods for structuring the output space, which is in accordance with the conclusions from the recent literature [17], [66]. Furthermore, data-driven hierarchies are generally better than the hierarchies created by an domain expert.…”

Section: A Structuring Large Output Spacessupporting

confidence: 84%

“…The results from the evaluation reveal that better predictive performance can be achieved by using data-driven approaches to construct the hierarchies rather than considering either, the flat multi-target regression task, or the pre-defined hierarchy created by a domain expert. Moreover, for large datasets, the results are in line with teh results for MLC [16], [17]: divisive hierarchy creation algorithms (balanced k-means and PCTs for clustering) are the best methods for clustering large output spaces. All in all, constructing a hierarchy of the target variables improves the predictive performance of the predictive models.…”

Section: Introductionsupporting

confidence: 82%

“…To the best of our knowledge, structuring of the target space for MTR has not been explored yet. Hence, we overview the methods for structuring the output space for the related multi-label classification (MLC) task where learning hierarchies in the output space has been studied to a wider extent [16], [17], [52]- [55].…”

Section: E Methods For Structuring the Output Spacementioning

confidence: 99%

“…Their results show that in general data-driven approach is superior to random created graphs of labels. Nikoloski et al (2017) [17] propose an algorithm for structuring the output space using feature ranking in MLC. They create a hierarchy from a space constructed by feature rankings for each of the classes.…”

Section: E Methods For Structuring the Output Spacementioning

confidence: 99%

“…The idea for structuring the output space in MLC proposed by [17] and [16] motivates the exploitation of methods for structuring the output space in MTR. In this study, we propose to transform a flat MTR task into a task of hierarchical multi-target regression (HMTR) [13].…”

Section: Structuring the Output Space For Mtrmentioning

confidence: 99%

See 4 more Smart Citations

Data-Driven Structuring of the Output Space Improves the Performance of Multi-Target Regressors

2019

Self Cite

View full text Add to dashboard Cite

The task of multi-target regression (MTR) is concerned with learning predictive models capable of predicting multiple target variables simultaneously. MTR has attracted an increasing attention within research community in recent years, yielding a variety of methods. The methods can be divided into two main groups: problem transformation and problem adaptation. The former transform a MTR problem into simpler (typically single target) problems and apply known approaches, while the latter adapt the learning methods to directly handle the multiple target variables and learn better models which simultaneously predict all of the targets. Studies have identified the latter group of methods as having competitive advantage over the former, probably due to the fact that it exploits the interrelations of the multiple targets. In the related task of multi-label classification, it has been recently shown that organizing the multiple labels into a hierarchical structure can improve predictive performance. In this paper, we investigate whether organizing the targets into a hierarchical structure can improve the performance for MTR problems. More precisely, we propose to structure the multiple target variables into a hierarchy of variables, thus translating the task of MTR into a task of hierarchical multi-target regression (HMTR). We use four data-driven methods for devising the hierarchical structure that cluster the real values of the targets or the feature importance scores with respect to the targets. The evaluation of the proposed methodology on 16 benchmark MTR datasets reveals that structuring the multiple target variables into a hierarchy improves the predictive performance of the corresponding MTR models. The results also show that data-driven methods produce hierarchies that can improve the predictive performance even more than expert constructed hierarchies. Finally, the improvement in predictive performance is more pronounced for the datasets with very large numbers (more than hundred) of targets.

show abstract

Section: A Structuring Large Output Spacessupporting

confidence: 84%

Section: Introductionsupporting

confidence: 82%

Section: E Methods For Structuring the Output Spacementioning

confidence: 99%

Section: E Methods For Structuring the Output Spacementioning

confidence: 99%

Section: Structuring the Output Space For Mtrmentioning

confidence: 99%

See 3 more Smart Citations

Data-Driven Structuring of the Output Space Improves the Performance of Multi-Target Regressors

2019

Self Cite

View full text Add to dashboard Cite

show abstract

Multi-label classification via closed frequent labelsets and label taxonomies

Ferrandin

Cerri

2023

Soft Comput

View full text Add to dashboard Cite

Multi-label classification (MLC) is a very explored field in recent years. The most common approaches that deal with MLC problems are classified into two groups: (i) problem transformation which aims to adapt the multi-label data, making the use of traditional binary or multiclass classification algorithms feasible, and (ii) algorithm adaptation which focuses on modifying algorithms used into binary or multiclass classification, enabling them to make multi-label predictions. Several approaches have been proposed aiming to explore the relationships among the labels, with some of them through the transformation of a flat multilabel label space into a hierarchical multi-label label space, creating a tree-structured label taxonomy and inducing a hierarchical multilabel classifier to solve the classification problem. This paper presents a novel method in which a label hierarchy structured as a directed acyclic graph (DAG) is created from the multi-label label space, taking into account the label co-occurrences using the notion of closed frequent labelset. With this, it is possible to solve an MLC task as if it was a hierarchical multi-label classification (HMC) task. Global and local HMC approaches were tested with the obtained label hierarchies and compared with the approaches using tree-structured label hierarchies showing very competitive results. The main advantage of Article Title the proposed approach is better exploration and representation of the relationships between labels through the use of DAG-structured taxonomies, improving the results. Experimental results over 32 multi-label datasets from different domains showed that the proposed approach is better than related approaches in most of the multi-label evaluation measures. Moreover, we found that both tree and in specially DAG-structured label hierarchies combined with a local hierarchical classifier are more suitable to deal with imbalanced multi-label datasets.

show abstract

A multi-label classification approach via hierarchical multi-label classification

Ferrandin

Cerri

2022

Preprint

View full text Add to dashboard Cite

Multi-label classification (MLC) is a very explored field in recent years. The most common approaches that deal with MLC problems are classified into two groups: (i) problem transformation which aims to adapt the multi-label data, making the use of traditional binary or multiclass classification algorithms feasible, and (ii) algorithm adaptation which focuses on modifying algorithms used into binary or multiclass classification, enabling them to make multi-label predictions. Several approaches have been proposed aiming to explore the relationships among the labels, with some of them through the transformation of a flat multi-label label space into a hierarchical multi-label label space, creating a tree-structured label taxonomy and inducing a hierarchical multi-label classifier to solve the classification problem. This paper presents a novel method in which a label hierarchy structured as a directed acyclic graph (DAG) is created from the multi-label label space, taking into account the label co-occurrences using the notion of closed frequent labelset. With this, it is possible to solve an MLC task as if it was a hierarchical multi-label classification (HMC) task. Global and local HMC approaches were tested with the obtained label hierarchies and compared with the approaches using tree-structured label hierarchies showing very competitive results. The main advantage of the proposed approach is better exploration and representation of the relationships between labels through the use of DAG-structured taxonomies, improving the results. Experimental results over 32 multi-label datasets from different domains showed that the proposed approach is better than related approaches in most of the multi-label evaluation measures. Moreover, we found that both tree and in specially DAG-structured label hierarchies combined with a local hierarchical classifier are more suitable to deal with imbalanced multi-label datasets.

show abstract

Structuring the Output Space in Multi-label Classification by Using Feature Ranking

Cited by 4 publications

References 14 publications

Data-Driven Structuring of the Output Space Improves the Performance of Multi-Target Regressors

Data-Driven Structuring of the Output Space Improves the Performance of Multi-Target Regressors

Multi-label classification via closed frequent labelsets and label taxonomies

A multi-label classification approach via hierarchical multi-label classification

Contact Info

Product

Resources

About