FINEST: Stabilizing Recommendations by Rank-Preserving Fine-Tuning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Oh, Sejoon, Ustun, Berk, McAuley, Julian, Kumar, Srijan
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911771379367936
author Oh, Sejoon
Ustun, Berk
McAuley, Julian
Kumar, Srijan
author_facet Oh, Sejoon
Ustun, Berk
McAuley, Julian
Kumar, Srijan
contents Modern recommender systems may output considerably different recommendations due to small perturbations in the training data. Changes in the data from a single user will alter the recommendations as well as the recommendations of other users. In applications like healthcare, housing, and finance, this sensitivity can have adverse effects on user experience. We propose a method to stabilize a given recommender system against such perturbations. This is a challenging task due to (1) the lack of a ``reference'' rank list that can be used to anchor the outputs; and (2) the computational challenges in ensuring the stability of rank lists with respect to all possible perturbations of training data. Our method, FINEST, overcomes these challenges by obtaining reference rank lists from a given recommendation model and then fine-tuning the model under simulated perturbation scenarios with rank-preserving regularization on sampled items. Our experiments on real-world datasets demonstrate that FINEST can ensure that recommender models output stable recommendations under a wide range of different perturbations without compromising next-item prediction accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03481
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FINEST: Stabilizing Recommendations by Rank-Preserving Fine-Tuning
Oh, Sejoon
Ustun, Berk
McAuley, Julian
Kumar, Srijan
Information Retrieval
Machine Learning
Social and Information Networks
Modern recommender systems may output considerably different recommendations due to small perturbations in the training data. Changes in the data from a single user will alter the recommendations as well as the recommendations of other users. In applications like healthcare, housing, and finance, this sensitivity can have adverse effects on user experience. We propose a method to stabilize a given recommender system against such perturbations. This is a challenging task due to (1) the lack of a ``reference'' rank list that can be used to anchor the outputs; and (2) the computational challenges in ensuring the stability of rank lists with respect to all possible perturbations of training data. Our method, FINEST, overcomes these challenges by obtaining reference rank lists from a given recommendation model and then fine-tuning the model under simulated perturbation scenarios with rank-preserving regularization on sampled items. Our experiments on real-world datasets demonstrate that FINEST can ensure that recommender models output stable recommendations under a wide range of different perturbations without compromising next-item prediction accuracy.
title FINEST: Stabilizing Recommendations by Rank-Preserving Fine-Tuning
topic Information Retrieval
Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2402.03481