NEAR: A Partner to Explain Any Factorised Recommender System

Files in This Item:
File Description SizeFormat 
insight_publication.pdf645.13 kBAdobe PDFDownload
Title: NEAR: A Partner to Explain Any Factorised Recommender System
Authors: Ouyang, SixunLawlor, Aonghus
Permanent link:
Date: 12-Jun-2019
Online since: 2019-07-08T10:37:58Z
Abstract: Many explainable recommender systems construct explanations of the recommendations these models produce, but it continues to be a difficult problem to explain to a user why an item was recommended by these high-dimensional latent factor models. In this work, We propose a technique that joint interpretations into recommendation training to make accurate predictions while at the same time learning to produce recommendations which have the most explanatory utility to the user. Our evaluation shows that we can jointly learn to make accurate and meaningful explanations with only a small sacrifice in recommendation accuracy. We also develop a new algorithm to measure explanation fidelity for the interpretation of top-n rankings. We prove that our approach can form the basis of a universal approach to explanation generation in recommender systems.
Funding Details: Science Foundation Ireland
Type of material: Conference Publication
Publisher: ACM
Start page: 247
End page: 249
Copyright (published version): 2019 the Authors
Keywords: Recommender systemsLearn to rankInterpretationExplanations
DOI: 10.1145/3314183.3323457
Other versions:
Language: en
Status of Item: Peer reviewed
Is part of: UMAP'19 Adjunct Adjunct Publication of the 27th Conference on User Modeling, Adaptation and Personalization
Conference Details: UMAP'19: 27th Conference on User Modeling, Adaptation and Personalization, Larnaca, Cyprus, 9-12 June 2019
ISBN: 978-1-4503-6711-0
Appears in Collections:Insight Research Collection

Show full item record

Page view(s)

checked on Jul 9, 2019


checked on Jul 9, 2019

Google ScholarTM



This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.