Criteria of Efficiency for Conformal Prediction

Vovk, Vladimir; Fedorova, Valentina; Nouretdinov, Ilia; Gammerman, Alexander

doi:10.1007/978-3-319-33395-3_2

Cited by 35 publications

(52 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The topic of this work is application of Conformal Prediction (CP) framework of reliable machine learning to big data. Conformal Prediction was developed in such works as [2,3]. Its main advantage is producing prediction sets that are valid in weak (i.i.d./exchangeability) assumptions.…”

Section: Topic Of the Workmentioning

confidence: 99%

“…In more details, efficiency of supervised learning were discussed in [3] while efficiency of conformal anomaly detection is discussed in detail in [6,8]. Some ways to measure efficiency numerically were presented in these works.…”

Section: Informative Efficiencymentioning

confidence: 99%

“…In [3] this principle was justified for supervised classification but can be easily adopted to anomaly detection as well. Further in Sec.…”

Section: Selection Of Conformity Measurementioning

confidence: 99%

“…, w k . Inspired by the logic of the work [3], we consider true data distribution as a limit (asymptotical) case of the empirical distribution, and the local density as a limit case of (the optimal) conformal density. We are analysing some asymptotical tendency, assuming that the amount of data in each of the sources is representative enough, so the difference between true and empirical distribution is low enough.…”

Section: Justification Of MC Approachmentioning

confidence: 99%

See 3 more Smart Citations

Validity and efficiency of conformal anomaly detection on big distributed data

Nouretdinov¹

2017

Adv. sci. technol. eng. syst. j.

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Topic Of the Workmentioning

confidence: 99%

Section: Informative Efficiencymentioning

confidence: 99%

“…In [3] this principle was justified for supervised classification but can be easily adopted to anomaly detection as well. Further in Sec.…”

Section: Selection Of Conformity Measurementioning

confidence: 99%

Section: Justification Of MC Approachmentioning

confidence: 99%

See 2 more Smart Citations

Validity and efficiency of conformal anomaly detection on big distributed data

Nouretdinov¹

2017

Adv. sci. technol. eng. syst. j.

Self Cite

View full text Add to dashboard Cite

show abstract

“…For conformal classifiers, efficiency can be expressed as a function of the number of class labels included in the prediction regions, given a specific confidence level [12].…”

Section: Introductionmentioning

confidence: 99%

Reliable Confidence Predictions Using Conformal Prediction

Linusson

Johansson

Boström

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Conformal classifiers output confidence prediction regions, i.e., multi-valued predictions that are guaranteed to contain the true output value of each test pattern with some predefined probability. In order to fully utilize the predictions provided by a conformal classifier, it is essential that those predictions are reliable, i.e., that a user is able to assess the quality of the predictions made. Although conformal classifiers are statistically valid by default, the error probability of the prediction regions output are dependent on their size in such a way that smaller, and thus potentially more interesting, predictions are more likely to be incorrect. This paper proposes, and evaluates, a method for producing refined error probability estimates of prediction regions, that takes their size into account. The end result is a binary conformal confidence predictor that is able to provide accurate error probability estimates for those prediction regions containing only a single class label.

show abstract

Chemical space exploration with Molpher: Generating and assessing a glucocorticoid receptor ligand library

Agea,

Čmelo,

Dehaen

et al. 2024

Molecular Informatics

View full text Add to dashboard Cite

Computational exploration of chemical space is crucial in modern cheminformatics research for accelerating the discovery of new biologically active compounds. In this study, we present a detailed analysis of the chemical library of potential glucocorticoid receptor (GR) ligands generated by the molecular generator, Molpher. To generate the targeted GR library and construct the classification models, structures from the ChEMBL database as well as from the internal IMG library, which was experimentally screened for biological activity in the primary luciferase reporter cell assay, were utilized. The composition of the targeted GR ligand library was compared with a reference library that randomly samples chemical space. A random forest model was used to determine the biological activity of ligands, incorporating its applicability domain using conformal prediction. It was demonstrated that the GR library is significantly enriched with GR ligands compared to the random library. Furthermore, a prospective analysis demonstrated that Molpher successfully designed compounds, which were subsequently experimentally confirmed to be active on the GR. A collection of 34 potential new GR ligands was also identified. Moreover, an important contribution of this study is the establishment of a comprehensive workflow for evaluating computationally generated ligands, particularly those with potential activity against targets that are challenging to dock.

show abstract

Criteria of Efficiency for Conformal Prediction

Cited by 35 publications

References 15 publications

Validity and efficiency of conformal anomaly detection on big distributed data

Validity and efficiency of conformal anomaly detection on big distributed data

Reliable Confidence Predictions Using Conformal Prediction

Chemical space exploration with Molpher: Generating and assessing a glucocorticoid receptor ligand library

Contact Info

Product

Resources

About