Decision tree and instance-based learning for label ranking

Cheng, Weiwei; Hühn, Jens Christian; Hüllermeier, Eyke

doi:10.1145/1553374.1553395

Cited by 103 publications

(258 citation statements)

References 8 publications

Supporting

Mentioning

258

Contrasting

Order By: Relevance

“…For this reason in the proposed clustering algorithms we assumed, and the experiments confirmed it, that likelihood maximization is an appropriate proxy criterion. Similar directions were taken in several other label ranking algorithms (Cheng et al 2009(Cheng et al , 2010.…”

Section: Prediction Measurementioning

confidence: 87%

“…), and that it cannot directly model incomplete label ranks. However, there are several papers (Cheng et al 2009;Dwork et al 2001;Lu and Boutilier 2011) that address these issues by introducing fast approximations which scale linearly with L, work well in practice, and can deal with partial rankings (Cheng et al 2009) and pairwise preferences (Lu and Boutilier 2011).…”

Section: Ranking Modelsmentioning

confidence: 99%

“…, N} , where x n is a d-dimensional feature vector and π n is a vector containing a total or partial order of a finite set Y of L class labels, is available for training. This problem has recently received a lot of attention in the machine learning community and has been extensively studied (Dekel et al 2003;Cheng et al 2009Cheng et al , 2010Har-Peled et al 2003;Qin et al 2010). A survey of recent label ranking algorithms can be found in Gärtner and Vembu (2010).…”

Section: Introductionmentioning

confidence: 99%

“…The second principled model, the RankTree model (RT) for clustering is an extension of previously proposed Decision Tree algorithm for label ranking (Cheng et al 2009). It performs supervised clustering by iteratively growing a tree to assign instances to clusters based on the current cluster central rankings, and recalculating cluster central rankings based on new assignments.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Supervised clustering of label ranking data using label preference information

et al. 2013

View full text Add to dashboard Cite

This paper studies supervised clustering in the context of label ranking data. The goal is to partition the feature space into K clusters, such that they are compact in both the feature and label ranking space. This type of clustering has many potential applications. For example, in target marketing we might want to come up with K different offers or marketing strategies for our target audience. Thus, we aim at clustering the customers' feature space into K clusters by leveraging the revealed or stated, potentially incomplete customer preferences over products, such that the preferences of customers within one cluster are more similar to each other than to those of customers in other clusters. We establish several baseline algorithms and propose two principled algorithms for supervised clustering. In the first baseline, the clusters are created in an unsupervised manner, followed by assigning a representative label ranking to each cluster. In the second baseline, the label ranking space is clustered first, followed by partitioning the feature space based on the central rankings. In the third baseline, clustering is applied on a new feature space consisting of both features and label rankings, followed by mapping back to the original feature and ranking space. The RankTree principled approach is based on a Ranking Tree algorithm previously proposed for label ranking prediction. Our modification starts with K random label rankings and iteratively splits the feature space to minimize the ranking loss, followed by re-calculation of the K rankings based on cluster assignments. The MM-PL approach is a Learn (2013) 93:191-225 multi-prototype supervised clustering algorithm based on the Plackett-Luce (PL) probabilistic ranking model. It represents each cluster with a union of Voronoi cells that are defined by a set of prototypes, and assign each cluster with a set of PL label scores that determine the cluster central ranking. Cluster membership and ranking prediction for a new instance are determined by cluster membership of its nearest prototype. The unknown cluster PL parameters and prototype positions are learned by minimizing the ranking loss, based on two variants of the expectation-maximization algorithm. Evaluation of the proposed algorithms was conducted on synthetic and real-life label ranking data by considering several measures of cluster goodness: (1) cluster compactness in feature space, (2) cluster compactness in label ranking space and (3) label ranking prediction loss. Experimental results demonstrate that the proposed MM-PL and RankTree models are superior to the baseline models. Further, MM-PL is has shown to be much better than other algorithms at handling situations with significant fraction of missing label preferences.

show abstract

Section: Prediction Measurementioning

confidence: 87%

Section: Ranking Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Supervised clustering of label ranking data using label preference information

et al. 2013

View full text Add to dashboard Cite

show abstract

“…Roughly speaking, the idea is to identify the query's k nearest neighbors in the instance space X , and then to combine the corresponding rankings into a prediction using suitable aggregation techniques. In [11], this approach was developed in a theoretically more sophisticated way, realizing the aggregation step in the form of maximum likelihood estimation based on a statistical model for rank data. Besides, this approach is also able to handle the more general case in which the rankings of the neighbored instances are only partially known.…”

Section: Local Aggregation Of Preferencesmentioning

confidence: 99%

Preference Learning: An Introduction

Fürnkranz¹,

Hüllermeier

2010

Preference Learning

Self Cite

102

View full text Add to dashboard Cite

Abstract. This introduction gives a brief overview of the field of preference learning and, along the way, tries to establish a unified terminology. Special emphasis will be put on learning to rank, which is by now one of the most extensively studied problem tasks in preference learning and also prominently represented in this book. We propose a categorization of ranking problems into object ranking, instance ranking, and label ranking. Moreover, we introduce these scenarios in a formal way, discuss different ways in which the learning of ranking functions can be approached, and explain how the contributions collected in this book relate to this categorization. Finally, we also highlight some important applications of preference learning methods.

show abstract

Consensus‐based journal rankings: A complementary tool for bibliometric evaluation

Aledo

Gámez

Melodelima

et al. 2018

Asso for Info Science & Tech

View full text Add to dashboard Cite

Annual journal rankings are usually considered a tool for the evaluation of research and researchers. Although they are an objective resource for such evaluation, they also present drawbacks: (a) the uncertainty about the definite position of a target journal in the corresponding annual ranking when selecting a journal, and (b) in spite of the nonsignificant difference in score (for instance, impact factor) between consecutive journals in the ranking, the journals are strictly ranked and eventually placed in different terciles/quartiles, which may have a significant influence in the subsequent evaluation. In this article we present several proposals to obtain an aggregated consensus ranking as an alternative/complementary tool to standardize annual rankings. To illustrate the proposed methodology we use as a case study the Journal Citation Reports, and in particular the category of Computer Science: Artificial Intelligence (CS:AI). In the context of the consensus rankings obtained by the different methods, we discuss the convenience of using one or the other procedure according to the corresponding framework. In particular, our proposals allow us to obtain consensus rankings that avoid crisp frontiers between similarly ranked journals and consider the longitudinal/temporal evolution of the journals.

show abstract

Decision tree and instance-based learning for label ranking

Cited by 103 publications

References 8 publications

Supervised clustering of label ranking data using label preference information

Supervised clustering of label ranking data using label preference information

Preference Learning: An Introduction

Consensus‐based journal rankings: A complementary tool for bibliometric evaluation

Contact Info

Product

Resources

About