Confidence Calibration for Recommender Systems and Its Applications

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Kweon, Wonbin
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916138502324224
author Kweon, Wonbin
author_facet Kweon, Wonbin
contents Despite the importance of having a measure of confidence in recommendation results, it has been surprisingly overlooked in the literature compared to the accuracy of the recommendation. In this dissertation, I propose a model calibration framework for recommender systems for estimating accurate confidence in recommendation results based on the learned ranking scores. Moreover, I subsequently introduce two real-world applications of confidence on recommendations: (1) Training a small student model by treating the confidence of a big teacher model as additional learning guidance, (2) Adjusting the number of presented items based on the expected user utility estimated with calibrated probability.
format Preprint
id arxiv_https___arxiv_org_abs_2402_16325
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Confidence Calibration for Recommender Systems and Its Applications
Kweon, Wonbin
Information Retrieval
Despite the importance of having a measure of confidence in recommendation results, it has been surprisingly overlooked in the literature compared to the accuracy of the recommendation. In this dissertation, I propose a model calibration framework for recommender systems for estimating accurate confidence in recommendation results based on the learned ranking scores. Moreover, I subsequently introduce two real-world applications of confidence on recommendations: (1) Training a small student model by treating the confidence of a big teacher model as additional learning guidance, (2) Adjusting the number of presented items based on the expected user utility estimated with calibrated probability.
title Confidence Calibration for Recommender Systems and Its Applications
topic Information Retrieval
url https://arxiv.org/abs/2402.16325