EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

kNNPC (k‐Nearest Neighbor Algorithm Per‐Class): Classification Method Predicting Extrapolation Regions With Reasonable Probability

Hiromasa Kaneko

Journal of Chemometrics · 2026-06 · 40 (6)

DOI: 10.1002/cem.70135 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemometrics, online erschienen am 14.05.2026. Verfasst von Hiromasa Kaneko. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In classification tasks, predicted class probabilities are often overconfident for samples outside the training distribution, which can lead to unsafe decision‐making. kNNPC, a k‐nearest neighbor algorithm per class, is proposed to mitigate such overconfidence under extrapolation or distribution shift. For a given test sample, kNNPC adjusts the predicted class‐probability vector so that it becomes closer to a maximum‐uncertainty distribution when the sample is dissimilar to the training data in the feature space. Importantly, kNNPC is not intended to identify extrapolation regions explicitly; rather, it provides a conservative probability output that serves as a practical safeguard against overconfident predictions. kNNPC was evaluated on benchmark and real‐world datasets, including the Iris dataset, a toxicity classification dataset, and a superconducting critical‐temperature dataset, and compares with standard probabilistic classifiers. The results indicate that kNNPC can effectively suppress overconfident probabilities for out‐of‐domain samples while maintaining comparable predictive performance. The Python code for the proposed method is available at https://github.com/hkaneko1985/dcekit .

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Kaneko, H. (2026). kNNPC (k‐Nearest Neighbor Algorithm Per‐Class): Classification Method Predicting Extrapolation Regions With Reasonable Probability. Journal of Chemometrics, 40(6). https://doi.org/10.1002/cem.70135

Vancouver

Kaneko H. kNNPC (k‐Nearest Neighbor Algorithm Per‐Class): Classification Method Predicting Extrapolation Regions With Reasonable Probability. Journal of Chemometrics. 2026;40(6). doi:10.1002/cem.70135

BibTeX
@article{Kaneko2026,
  author = {Kaneko, Hiromasa},
  title = {kNNPC (k‐Nearest Neighbor Algorithm Per‐Class): Classification Method Predicting Extrapolation Regions With Reasonable Probability},
  journal = {Journal of Chemometrics},
  year = {2026},
  volume = {40},
  number = {6},
  doi = {10.1002/cem.70135}
}
Kostenlos starten →