Deep learning-based recommender systems are nowadays defining the state-of-the-art. Unfortunately, their hard interpretability restrains their application in scenarios in which explainability is required/desirable. Many efforts have been devoted to injecting explainable information inside deep models. However, there is still a lot of work that needs to be done to fill this gap. In this paper, we take a step in this direction by providing an intuitive interpretation of the inner representation of a conditioned variational autoencoder (C-VAE) for collaborative filtering. The interpretation is visually performed by plotting the principal components of the latent space learned by the model on MovieLens. We show that in the latent space conditions on correlated genres map users in close clusters. This characteristic enables the model to be used for profiling purposes.

A Look Inside the Black-Box: Towards the Interpretability of Conditioned Variational Autoencoder for Collaborative Filtering

Polato M.;
2020-01-01

Abstract

Deep learning-based recommender systems are nowadays defining the state-of-the-art. Unfortunately, their hard interpretability restrains their application in scenarios in which explainability is required/desirable. Many efforts have been devoted to injecting explainable information inside deep models. However, there is still a lot of work that needs to be done to fill this gap. In this paper, we take a step in this direction by providing an intuitive interpretation of the inner representation of a conditioned variational autoencoder (C-VAE) for collaborative filtering. The interpretation is visually performed by plotting the principal components of the latent space learned by the model on MovieLens. We show that in the latent space conditions on correlated genres map users in close clusters. This characteristic enables the model to be used for profiling purposes.
2020
International Conference on User Modelling, Adaptation, and Personalization
Genova, Italy
2020
UMAP 2020 Adjunct - Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization
Association for Computing Machinery, Inc
233
236
9781450379502
collaborative filtering; explainability; interpretability; recommender systems; variational autoencoder
Carraro T.; Polato M.; Aiolli F.
File in questo prodotto:
File Dimensione Formato  
exum06s.pdf

Accesso aperto

Tipo di file: PREPRINT (PRIMA BOZZA)
Dimensione 1.53 MB
Formato Adobe PDF
1.53 MB Adobe PDF Visualizza/Apri
3386392.3399305.pdf

Accesso riservato

Tipo di file: PDF EDITORIALE
Dimensione 2.01 MB
Formato Adobe PDF
2.01 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1870203
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? ND
social impact