entity2rec: Property-specific knowledge graph embeddings for item recommendation
| Autor: | Elena Baralis, Giuseppe Rizzo, Raphaël Troncy, Enrico Palumbo, Diego Monti |
|---|---|
| Přispěvatelé: | Istituto Superiore Mario Boella (ISMB), EURECOM, Eurecom [Sophia Antipolis]-Centre National de la Recherche Scientifique (CNRS), Politecnico di Torino = Polytechnic of Turin (Polito) |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
02 engineering and technology Recommender system Machine learning computer.software_genre Artificial Intelligence 020204 information systems 0202 electrical engineering electronic engineering information engineering Collaborative filtering [INFO]Computer Science [cs] knowledge graph embeddings Serendipity business.industry General Engineering Novelty Random walk Popularity Graph Computer Science Applications knowledge graphs recommender systems knowledge graph embeddings knowledge graphs 020201 artificial intelligence & image processing Artificial intelligence recommender systems business computer |
| Zdroj: | Expert Systems with Applications Expert Systems with Applications, Elsevier, 2020, 151, pp.113235-. ⟨10.1016/j.eswa.2020.113235⟩ |
| ISSN: | 0957-4174 |
| Popis: | Knowledge graphs have shown to be highly beneficial to recommender systems, providing an ideal data structure to generate hybrid recommendations using both content-based and collaborative filtering. Most knowledge-aware recommender systems are based on manually engineered features, typically relying on path counting and/or on random walks. Recently, knowledge graph embeddings have proven to be extremely effective at learning features for prediction tasks, reducing the complexity and time required to manually design effective features. In this work, we present entity2rec, which learns user-item relatedness for item recommendation through property-specific knowledge graph embeddings. A key element of entity2rec is the construction of property-specific subgraphs. Through an extensive evaluation on three datasets, we show that: (1) hybrid property-specific subgraphs consistently enhance the quality of recommendations with respect to collaborative and content-based subgraphs; (2) entity2rec generates accurate and non-obvious recommendations, compared to a set of state-of-the-art recommender systems, achieving high accuracy, serendipity and novelty. More in detail, entity2rec is particularly effective when the dataset is sparse and has a low popularity bias; (3) entity2rec is easily interpretable and can thus be configured for a particular recommendation problem. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect