About: Hierarchical Gradient Smoothing for Probability Estimation Trees

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Hierarchical Gradient Smoothing for Probability Estimation Trees Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Hierarchical Gradient Smoothing for Probability Estimation Trees
Creator	Zhang, He Buntine, Wray Petitjean, François
Source	PMC
abstract	Decision trees are still seeing use in online, non-stationary and embedded contexts, as well as for interpretability. For applications like ranking and cost-sensitive classification, probability estimation trees (PETs) are used. These are built using smoothing or calibration techniques. Older smoothing techniques used counts local to a leaf node, but a few more recent techniques consider the broader context of a node when doing estimation. We apply a recent advanced smoothing method called Hierarchical Dirichlet Process (HDP) to PETs, and then propose a novel hierarchical smoothing approach called Hierarchical Gradient Smoothing (HGS) as an alternative. HGS smooths leaf nodes up to all the ancestors, instead of recursively smoothing to the parent used by HDP. HGS is made faster by efficiently optimizing the Leave-One-Out Cross-Validation (LOOCV) loss measure using gradient descent, instead of sampling used in HDP. An extensive set of experiments are conducted on 143 datasets showing that our HGS estimates are not only more accurate but also do so within a fraction of HDP time. Besides, HGS makes a single tree almost as good as a Random Forest with 10 trees. For applications that require more interpretability and efficiency, a single decision tree plus HGS is more preferred.
has issue date	2020-04-17(xsd:dateTime)
bibo:doi	10.1007/978-3-030-47426-3_18
has license	no-cc
sha1sum (hex)	001c647797abea963cbbd93fc85932ab96f00482
schema:url	https://doi.org/10.1007/978-3-030-47426-3_18
resource representing a document's title	Hierarchical Gradient Smoothing for Probability Estimation Trees
has PubMed Central identifier	PMC7206292
schema:publication	Advances in Knowledge Discovery and Data Mining
resource representing a document's body	covid:001c647797abea963cbbd93fc85932ab96f00482#body_text
is schema:about of	named entity 'ACCURATE' named entity 'ALTERNATIVE' named entity 'SAMPLING' named entity 'HGS' named entity 'COST' named entity 'USING' named entity 'NOVEL' named entity 'USED BY' named entity 'PETS' named entity 'NODE' named entity 'gradient descent' named entity 'decision tree' named entity 'leaf nodes' named entity 'Decision trees' named entity 'HDP' named entity 'smoothing techniques' named entity 'HDP' named entity 'HDP' named entity 'probability estimation' named entity 'Probability Estimation' named entity 'Internet of Things' named entity 'decision tree' named entity 'decision tree' named entity 'HDP' named entity 'gradient descent' named entity 'HDP' named entity 'HDP' named entity 'gradient descent' named entity 'RMSE' named entity 'global optimization' named entity 'inference process' named entity 'decision tree' named entity 'smoothing techniques' named entity 'M-estimation' named entity 'probability estimation' named entity 'algorithm' named entity 'Laplace smoothing' named entity 'Random Forest' named entity 'LOOCV' named entity 'LOOCV' named entity 'RMSE' named entity 'decision trees' named entity 'Bayesian network' named entity 'gradient descent' named entity 'UCI' named entity 'Laplace' named entity 'Leave-One-Out' named entity 'source code' named entity 'Laplace smoothing' named entity 'Maximum Likelihood Estimation' named entity 'Classifiers' named entity '0.01' named entity 'Laplace smoothing' named entity 'LOO' named entity '0-1 Loss' named entity 'decision trees' named entity 'RMSE' named entity 'experimental settings' named entity 'decision tree' named entity 'smoothing techniques' named entity 'leaf node' named entity 'LOO' named entity 'UCI' named entity 'LOO' named entity 'running time' named entity 'decision trees' named entity 'random forest' named entity 'M-estimation' named entity 'algorithm' named entity 'LOOCV' named entity 'Bayesian Network' named entity 'random forest' named entity 'gradient descent' named entity 'log loss' named entity 'Gibbs sampling' named entity 'loss functions' named entity 'HDP' named entity 'HDP' named entity '0-1 Loss' named entity 'algorithm' named entity 'HDP'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software