dTrust: a simple deep learning approach for social recommendation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

dTrust: a simple deep learning approach for social recommendation


Rating prediction is a key task of e-commerce recommendation mechanisms. Recent studies in social recommendation enhance the performance of rating predictors by taking advantage of user relationships. However, these prediction approaches mostly rely on user personal information which is a privacy threat. In this paper, we present dTrust, a simple social recommendation approach that avoids using user personal information. It relies uniquely on the topology of an anonymized trust-user-item network that combines user trust relations with user rating scores. This topology is fed into a deep feed-forward neural network. Experiments on real-world data sets showed that dTrust outperforms state-of-the-art in terms of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) scores for both warm-start and cold-start problems.
Fichier principal
Vignette du fichier
PID5013211.pdf (505.68 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01578316 , version 1 (29-08-2017)
hal-01578316 , version 2 (06-09-2017)
hal-01578316 , version 3 (15-09-2017)


  • HAL Id : hal-01578316 , version 3


Quang-Vinh Dang, Claudia-Lavinia Ignat. dTrust: a simple deep learning approach for social recommendation. The 3rd IEEE International Conference on Collaboration and Internet Computing (CIC-17), Oct 2017, San Jose, United States. ⟨hal-01578316v3⟩
592 View
968 Download


Gmail Facebook X LinkedIn More