Uncertainty-adjusted Inductive Matrix Completion with Graph Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F23%3A00368260" target="_blank" >RIV/68407700:21240/23:00368260 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1145/3604915.3610654" target="_blank" >https://doi.org/10.1145/3604915.3610654</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3604915.3610654" target="_blank" >10.1145/3604915.3610654</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Uncertainty-adjusted Inductive Matrix Completion with Graph Neural Networks

Popis výsledku v původním jazyce

We propose a robust recommender systems model which performs matrix completion and a ratings-wise uncertainty estimation jointly. Whilst the prediction module is purely based on an implicit low-rank assumption imposed via nuclear norm regularization, our loss function is augmented by an uncertainty estimation module which learns an anomaly score for each individual rating via a Graph Neural Network: data points deemed more anomalous by the GNN are downregulated in the loss function used to train the low-rank module. The whole model is trained in an end-to-end fashion, allowing the anomaly detection module to tap on the supervised information available in the form of ratings. Thus, our model’s predictors enjoy the favourable generalization properties that come with being chosen from small function space (i.e., low-rank matrices), whilst exhibiting the robustness to outliers and flexibility that comes with deep learning methods. Furthermore, the anomaly scores themselves contain valuable qualitative information. Experiments on various real-life datasets demonstrate that our model outperforms standard matrix completion and other baselines, confirming the usefulness of the anomaly detection module.

Název v anglickém jazyce

Uncertainty-adjusted Inductive Matrix Completion with Graph Neural Networks

Popis výsledku anglicky

We propose a robust recommender systems model which performs matrix completion and a ratings-wise uncertainty estimation jointly. Whilst the prediction module is purely based on an implicit low-rank assumption imposed via nuclear norm regularization, our loss function is augmented by an uncertainty estimation module which learns an anomaly score for each individual rating via a Graph Neural Network: data points deemed more anomalous by the GNN are downregulated in the loss function used to train the low-rank module. The whole model is trained in an end-to-end fashion, allowing the anomaly detection module to tap on the supervised information available in the form of ratings. Thus, our model’s predictors enjoy the favourable generalization properties that come with being chosen from small function space (i.e., low-rank matrices), whilst exhibiting the robustness to outliers and flexibility that comes with deep learning methods. Furthermore, the anomaly scores themselves contain valuable qualitative information. Experiments on various real-life datasets demonstrate that our model outperforms standard matrix completion and other baselines, confirming the usefulness of the anomaly detection module.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

RecSys '23: Proceedings of the 17th ACM Conference on Recommender Systems

ISBN

979-8-4007-0241-9

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

1169-1174

Název nakladatele

Association for Computing Machinery

Místo vydání

New York

Místo konání akce

Singapur

Datum konání akce

18. 9. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001156630300147