Kernel Density Estimation for Multiclass Quantification ...
arXiv, 2024
report
Zugriff:
Several disciplines, like the social sciences, epidemiology, sentiment analysis, or market research, are interested in knowing the distribution of the classes in a population rather than the individual labels of the members thereof. Quantification is the supervised machine learning task concerned with obtaining accurate predictors of class prevalence, and to do so particularly in the presence of label shift. The distribution-matching (DM) approaches represent one of the most important families among the quantification methods that have been proposed in the literature so far. Current DM approaches model the involved populations by means of histograms of posterior probabilities. In this paper, we argue that their application to the multiclass setting is suboptimal since the histograms become class-specific, thus missing the opportunity to model inter-class information that may exist in the data. We propose a new representation mechanism based on multivariate densities that we model via kernel density ... : fixed broken references to appendices ...
Titel: |
Kernel Density Estimation for Multiclass Quantification ...
|
---|---|
Autor/in / Beteiligte Person: | Moreo, Alejandro ; González, Pablo ; del Coz, Juan José |
Link: | |
Veröffentlichung: | arXiv, 2024 |
Medientyp: | report |
DOI: | 10.48550/arxiv.2401.00490 |
Schlagwort: |
|
Sonstiges: |
|