![](https://csdnimg.cn/release/download_crawler_static/12280937/bg7.jpg)
A review on deep learning for recommender systems: challenges…
CF systems rely on the rating history of the items given by the users of the system. Sparsity
appears as a major problem especially for CF since the users only rate a small fraction of the
available items, which makes it challenging to generate predictions (Su and Khoshgoftaar
2009; Bobadilla et al. 2013). When working on a sparse dataset, a CF algorithm may fail
to take advantage of beneficial relationships among users and items. Data sparsity leads to
another severe challenge referred to as the cold-start problem. Producing predictions for
a new user having very few ratings is not possible due to insufficient data to profile them.
Likewise, presenting recently added items as recommendations to users is also not achievable
due to the lack of ratings for those items. However, unlike CF techniques, newly added users
and items can be managed in content-based recommender systems by utilizing their content
information.
Most of the recommender systems are deployed in a responsive environment. In a typical
recommendation scenario, a user is provided with a set of recommended items according
to her preferences while she is navigating through a web page. In order to carry out such
scenario efficiently, the recommendations should be provided in a reasonable amount of
time, which requires a highly-scalable system (Linden et al. 2003). With the growth of the
number of users and/or items in the system, many algorithms tend to slow down or require
more computational resources (Shani and Gunawardana 2011). Thus, scalability turns into a
significant challenge that should be managed efficiently.
3.2 Deep learning
Deep learning is a field of machine learning that is based on learning several layers of
representations, typically by using artificial neural networks. Through the layer hierarchy of
a deep learning model, the higher-level concepts are defined from the lower-level concepts
(Deng and Yu 2014).
Since Hinton et al. (2006) introduced an efficient way of training deep models and Bengio
(2009) showed the capabilities of deep architectures in complicated artificial intelligence
tasks, deep learning has become an emerging topic in computer science. Currently, deep
learning approaches produce the state-of-the-art solutions to many problems in computer
vision, natural language processing, and speech recognition (Deng and Yu 2014).
Although neural networks and the science behind deep models have been around for more
than 50 years, the power of deep learning techniques has started revealing during the last
decade. The main factors that promote deep learning as the state-of-the-art machine learning
technique can be listed as follows:
Big data: A deep learning model learns better representations as it is provided with more
amount of data.
Computational power: Graphical processing units (GPU) meet the processing power
required for complex computations in deep learning models.
Throughout this section, we briefly introduce the deep learning models that have been
widely utilized in recommendation tasks.
3.2.1 Restricted Boltzmann machines
A restricted Boltzmann machine (RBM) is a particular type of a Boltzmann machine, which
has two layers of units. As illustrated in Fig. 2, the first layer consists of visible units, and the
second layer includes hidden units. In this restricted architecture, there are no connections
between the units in a layer (Salakhutdinov and Hinton 2009).
123