Exploiting and Exploring Hierarchical Structure in Music Recommendation

Recommender Systems with Heterogeneous Side Information

“…Despite of its success, collaborative filtering approaches are known to suffer from data sparsity issues, as the number of items or users is typically very large but the number of ratings is relatively small. One popular way to address this issue is to incorporate the increasingly available side information in the model [2,5,15,28,29,31]. The majority of studies exploit either only flat side information [2,5], or only hierarchical side information [15,31] due to the challenges brought by the inherent difference between these two types of information.…”

“…Such side information provides independent sources for recommendations, which can mitigate the data sparsity and cold start problems and have great potentials to boost the performance. As a consequence, a large body of research has been developed to exploit side information for recommendations [15,23,31,32]. Side information is typically heterogeneous, which can be roughly categorized into flat and hierarchical side information [31].…”

“…Likewise, users are also associated with both flat information such as age, gender, education level and hierarchical information such as communities they belong to and the places of their birth. There are numerous works incorporating flat or hierarchical side information for recommendations [5,15,21,23,31,32]. Most of these systems have been designed to exploit either only flat side information or only hierarchical side information.…”

Regularized deep learning for fashion and social media data analysis

“…For example, in Netflix DVD rental page, a hierarchical structure is applied to categorize movies as genre → sub-genre → detailedcategory 1 . Based on the hierarchical structure in real-word recommendation system, exploiting the hierarchical latent factors of items or users attracted a lot of attentions by researchers recently [128,129], and the hierarchical structure has demonstrated its effectiveness. However, these works only focused on the single domain recommendation, instead of the cross-domain scenario.…”

“…In recommendation system, for example, in Netflix DVD rental page, movies are usually categorized as a hierarchical structure as genre → sub-genre → detailed-category. As shown in To capture the hierarchical structures in real-world recommendation system, recently, exploring the hierarchical items or users latent factors attracted a lot of attentions [128,129,137].…”