In the past years, knowledge graphs have proven to be beneficial for recommender systems, efficiently addressing paramount issues such as new items and data sparsity. At the same time, several works have recently tackled the problem of knowledge graph completion through machine learning algorithms able to learn knowledge graph embeddings. In this paper, we show that the item recommendation problem can be seen as a specific case of knowledge graph completion problem, where the “feedback” property, which connects users to items that they like, has to be predicted. We empirically compare a set of state-of-the-art knowledge graph embeddings algorithms on the task of item recommendation on the Movielens 1M dataset. The results show that knowledge graph embeddings models outperform traditional collaborative filtering baselines and that TransH obtains the best performance.

An empirical comparison of knowledge graph embeddings for item recommendation / Palumbo, Enrico; Rizzo, Giuseppe; Troncy, Raphael; Baralis, ELENA MARIA; Osella, Michele; Ferro, ENRICO GIOVANNI. - ELETTRONICO. - 2106:(2018). (Intervento presentato al convegno Extended Semantic Web Conference 2018).

An empirical comparison of knowledge graph embeddings for item recommendation

Enrico Palumbo;Giuseppe Rizzo;Elena Baralis;Michele Osella;Enrico Ferro
2018

Abstract

In the past years, knowledge graphs have proven to be beneficial for recommender systems, efficiently addressing paramount issues such as new items and data sparsity. At the same time, several works have recently tackled the problem of knowledge graph completion through machine learning algorithms able to learn knowledge graph embeddings. In this paper, we show that the item recommendation problem can be seen as a specific case of knowledge graph completion problem, where the “feedback” property, which connects users to items that they like, has to be predicted. We empirically compare a set of state-of-the-art knowledge graph embeddings algorithms on the task of item recommendation on the Movielens 1M dataset. The results show that knowledge graph embeddings models outperform traditional collaborative filtering baselines and that TransH obtains the best performance.
File in questo prodotto:
File Dimensione Formato  
paper2.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 494.14 kB
Formato Adobe PDF
494.14 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

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/11583/2710124
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo