The Role of Hubs in Cross-Lingual Supervised Document Retrieval

Tomašev, Nenad; Rupnik, Jan; Mladenić, Dunja

doi:10.1007/978-3-642-37456-2_16

Cited by 14 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hubness-aware methods have been proposed for data reduction [15], ranking [80], representation learning [82], metric learning [71,72,76,79], classification [77,78,81], outlier detection [67], and clustering [83].…”

Section: Hubness: the Long Tail Of Relevance And The Central Tendencimentioning

confidence: 99%

Clustering Evaluation in High-Dimensional Data

Tomašev

Radovanović

2016

Unsupervised Learning Algorithms

Self Cite

View full text Add to dashboard Cite

Clustering evaluation plays an important role in unsupervised learning systems, as it is often necessary to automatically quantify the quality of generated cluster configurations. This is especially useful for comparing the performance of different clustering algorithms as well as determining the optimal number of clusters in clustering algorithms that do not estimate it internally. Many clustering quality indexes have been proposed over the years and different indexes are used in different contexts. There is no unifying protocol for clustering evaluation, so it is often unclear which quality index to use in which case. In this chapter, we review the existing clustering quality measures and evaluate them in the challenging context of high-dimensional data clustering. High-dimensional data is sparse and distances tend to concentrate, possibly affecting the applicability of various clustering quality indexes. We analyze the stability and discriminative power of a set of standard clustering quality measures with increasing data dimensionality. Our evaluation shows that the curse of dimensionality affects different clustering quality indexes in different ways and that some are to be preferred when determining clustering quality in many dimensions.

show abstract

Section: Hubness: the Long Tail Of Relevance And The Central Tendencimentioning

confidence: 99%

Clustering Evaluation in High-Dimensional Data

Tomašev

Radovanović

2016

Unsupervised Learning Algorithms

Self Cite

View full text Add to dashboard Cite

show abstract

“…The phenomenon was initially attributed to the particular representations and metrics that were standard at the time. However, as subsequent analysis has shown, hubness is ubiquitous in intrinsically high-dimensional data and has since been confirmed in images [53,71,72], text [55,75,77], time series [56], collaborative filtering data [48], etc. In general, most data that is encountered today in practical machine learning and data mining applications is highly complex and intrinsically high-dimensional.…”

Section: Application Domains and Other Types Of Hubness-aware Methodsmentioning

confidence: 98%

Hubness-Based Clustering of High-Dimensional Data

Tomašev

Radovanović

Mladenić

et al. 2014

Partitional Clustering Algorithms

Self Cite

View full text Add to dashboard Cite

Hubness has recently been established as a significant property of k-nearest neighbor (k-NN) graphs obtained from high-dimensional data using a distance measure, with traits and effects relevant to the cluster structure of data, as well as clustering algorithms. The hubness property is manifested with increasing (intrinsic) data dimensionality. The distribution of data point in-degrees, i.e. the number of times points appear among the k nearest neighbors of other points in the data, becomes highly skewed. This results in hub points that can have in-degrees multiple orders of magnitude higher than expected. In this chapter we review and refine existing work which explains the mechanisms of the phenomenon, establishes the location of hub points near central regions of clusters in the data, and shows how hubness can negatively affect existing clustering algorithms by virtue of hub points lowering between-cluster distance. Next, we review the newly proposed partitional clustering algorithms, based on K-means, which take advantage of hubness by employing hubs in the process of cluster prototype selection. These "soft" K-means extensions avoid premature convergence to suboptimal stable cluster configurations and are able to reach the global optima more often. The algorithms offer significant improvements over the K-means baseline in scenarios involving high-dimensional and noisy data. The improvements stem from a better placement of hub points into clusters, which helps in increasing the between-cluster distance. Finally, we introduce novel clustering algorithms as "kernelized" versions of the most successful hubness-based methods discussed above, that are able to more effectively handle arbitrarily-shaped clusters.

show abstract

“…Hubs were shown to be relevant in various contexts, including text mining [45], [46], music retrieval and recommendation [47], [48], [49], [50], image data [51], [52] and time series [34], [53].…”

Section: Hubs In Eeg Datamentioning

confidence: 99%

Classification of Electroencephalograph Data: A Hubness-aware Approach

2016

APH

View full text Add to dashboard Cite

show abstract

The Role of Hubs in Cross-Lingual Supervised Document Retrieval

Cited by 14 publications

References 20 publications

Clustering Evaluation in High-Dimensional Data

Clustering Evaluation in High-Dimensional Data

Hubness-Based Clustering of High-Dimensional Data

Classification of Electroencephalograph Data: A Hubness-aware Approach

Contact Info

Product

Resources

About