Attribute-Aware Recommender System Based on Collaborative Filtering: Survey and Classification

Abstract

A ribute-aware CF models aims at rating prediction given not only the historical rating from users to items, but also the information associated with users (e.g. age), items (e.g. price), or even ratings (e.g. rating time). is paper surveys works in the past decade developing a ribute-aware CF systems, and discovered that mathematically they can be classi ed into four di erent categories. We provide the readers not only the high level mathematical interpretation of the existing works in this area but also the mathematical insight for each category of models. Finally we provide in-depth experiment results comparing the e ectiveness of the major works in each category.

An Attention-Based Latent Information Extraction Network (ALIEN) for High-Order Feature Interactions

“…Attributes-driven latent information extraction layer (USER × CANDIDATE): This layer performs a macro task of learning the latent information from modeling the low and high-order feature interactions, thereby establishing the contribution of each feature interaction to the user u's interest. Modeling low and high-order feature interactions from user and item attributes is overlooked by many recommendation models [7,10]. In addition, in their models, user and item embeddings u and v are initialized only with indices of u and v, which have vague meanings and converge slowly.…”

“…Thereafter a user's interaction with an item is modeled as the inner product of their latent vectors. Recently, researchers have been embracing deep-learning neural architectures that can learn very complicated functions from data, to replace the inner product applied in matrix factorization [6,7] and also include information from history sequences [8,9]. However, even with (a) user-user similarity (based on, e.g., clicks), and (b) history sequences, there is still another source of information which emerges from (c) the "attributes" (sometime called "features") of users and items, and the interactions of these attributes, originally at the main effect level, but that is now moving to the second, third and even higher-order interactions.…”

“…The user's attributes include demographic factors, e.g., age, gender, occupation and educational background [7,[10][11][12][13][14]. In addition, item attributes such as the category of a product, the genre of a movie and the release date of an album, not only render the basic information about the item, but also provide clues as to why the user is interested in it [10,15].…”

On Variational Inference for User Modeling in Attribute-Driven Collaborative Filtering

“…The use of loyalty is motivated by works such as [11], where the authors model consumers' repeat purchase behavior, as well as our experience in the domain of e-Commerce and grocery. Attribute-based collaborative filtering has been explored before in works such as [12] where the authors use categorical attributes to improve recommendation through multi-task learning or hierarchical classification, and [13] which deals with attribute-aware collaborative filtering. Our work captures the changing affinity of the users to these attributes, and thus could be used as a first stage in hierarchical classification algorithms: to predict which brands the users will buy next, before recommending particular items of that brand.…”

Multi-criteria– Recommendations using Autoencoder and Deep Neural Networks with Weight Optimization using Firefly Algorithm

“…These Systems are known as Attribute-aware Recommender systems (AaRS). As for the previous research [14], these AaRS can be classified into four types namely: (i) Discriminate Matrix factorization (ii) Generative Matrix factorization (iii) Factorization Machines and (iv) Heterogeneous graphs. The variation of these categories comes from user, product and attributes interactions.…”