Deep Learning and factorization-based collaborative filtering recommendation models have undoubtedly dominated the scene of recommender systems in recent years. However, despite their outstanding performance, these methods require a training time proportional to the size of the embeddings and it further increases when also side information is considered for the computation of the recommendation list. In fact, in these cases we have that with a large number of high-quality features, the resulting models are more complex and difficult to train. This paper addresses this problem by presenting KGFlex: a sparse factorization approach that grants an even greater degree of expressiveness. To achieve this result, KGFlex analyzes the historical data to understand the dimensions the user decisions depend on (e.g., movie direction, musical genre, nationality of book writer). KGFlex represents each item feature as an embedding and it models user-item interactions as a factorized entropy-driven combination of the item attributes relevant to the user. KGFlex facilitates the training process by letting users update only those relevant features on which they base their decisions. In other words, the user-item prediction is mediated by the user's personal view that considers only relevant features. An extensive experimental evaluation shows the approach's effectiveness, considering the recommendation results' accuracy, diversity, and induced bias. The public implementation of KGFlex is available at https://split.to/kgflex.

Sparse Feature Factorization for Recommender Systems with Knowledge Graphs / Walter Anelli, Vito; Di Noia, Tommaso; Di Sciascio, Eugenio; Ferrara, Antonio; Mancino, ALBERTO CARLO MARIA. - (2021), pp. 154-165. (Intervento presentato al convegno ACM Conference on Recommender Systems tenutosi a Amsterdam; The Netherlands) [10.1145/3460231.3474243].

Sparse Feature Factorization for Recommender Systems with Knowledge Graphs

Alberto Carlo Maria Mancino
2021

Abstract

Deep Learning and factorization-based collaborative filtering recommendation models have undoubtedly dominated the scene of recommender systems in recent years. However, despite their outstanding performance, these methods require a training time proportional to the size of the embeddings and it further increases when also side information is considered for the computation of the recommendation list. In fact, in these cases we have that with a large number of high-quality features, the resulting models are more complex and difficult to train. This paper addresses this problem by presenting KGFlex: a sparse factorization approach that grants an even greater degree of expressiveness. To achieve this result, KGFlex analyzes the historical data to understand the dimensions the user decisions depend on (e.g., movie direction, musical genre, nationality of book writer). KGFlex represents each item feature as an embedding and it models user-item interactions as a factorized entropy-driven combination of the item attributes relevant to the user. KGFlex facilitates the training process by letting users update only those relevant features on which they base their decisions. In other words, the user-item prediction is mediated by the user's personal view that considers only relevant features. An extensive experimental evaluation shows the approach's effectiveness, considering the recommendation results' accuracy, diversity, and induced bias. The public implementation of KGFlex is available at https://split.to/kgflex.
2021
ACM Conference on Recommender Systems
feature factorization; entropy; knowledge graphs; recommender systems
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Sparse Feature Factorization for Recommender Systems with Knowledge Graphs / Walter Anelli, Vito; Di Noia, Tommaso; Di Sciascio, Eugenio; Ferrara, Antonio; Mancino, ALBERTO CARLO MARIA. - (2021), pp. 154-165. (Intervento presentato al convegno ACM Conference on Recommender Systems tenutosi a Amsterdam; The Netherlands) [10.1145/3460231.3474243].
File allegati a questo prodotto
File Dimensione Formato  
Anelli_Sparse_2021.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 4.13 MB
Formato Adobe PDF
4.13 MB Adobe PDF   Contatta l'autore
Anelli_postprint_Sparse_2021.pdf

accesso aperto

Note: https://doi.org/10.1145/3460231.3474243
Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 4.04 MB
Formato Adobe PDF
4.04 MB Adobe PDF

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/11573/1623318
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 22
  • ???jsp.display-item.citation.isi??? 12
social impact