General factorization framework for context-aware recommendations

By Balázs Hidasi, Domonkos Tikk. 2014

112 citations recorded by the source corpus.

Context-aware recommendation algorithms focus on refining recommendations by considering additional information, available to the system. This topic has gained a lot of attention recently. Among others, several factorization methods were proposed to solve the problem, although most of them assume explicit feedback which strongly limits their real-world applicability. While these algorithms apply various loss functions and optimization strategies, the preference modeling under context is less explored due to the lack of tools allowing for easy experimentation with various models. As context dimensions are introduced beyond users and items, the space of possible preference models and the importance of proper modeling largely increases. In this paper we propose a general factorization framework (GFF), a single flexible algorithm that takes the preference model as an input and computes latent feature matrices for the input dimensions. GFF allows us to easily experiment with various linear models on any context-aware recommendation task, be it explicit or implicit feedback based. The scaling properties makes it usable under real life circumstances as well. We demonstrate the framework’s potential by exploring various preference models on a 4-dimensional context-aware problem with contexts that are available for almost any real life datasets. We show in our experiments—performed on five real life, implicit feedback datasets—that proper preference modelling significantly increases recommendation accuracy, and previously unused models outperform the traditional ones. Novel models in GFF also outperform state-of-the-art factorization algorithms. We also extend the method to be fully compliant to the Multidimensional Dataspace Model, one of the most extensive data models of context-enriched data. Extended GFF allows the seamless incorporation of information into the factorization framework beyond context, like item metadata, social networks, session information, etc. Preliminary experiments show great potential of this capability.

Subfields: Computer Networks and Communications, Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

In Signal Processing

Citations in the corpus

Contextual Sequence Modeling for Recommendation with Recurrent Neural Networks (2017, background): “Hidasi and Tikk [8] introduced a general framework that models interactions between user, items and context in the latent space through multiplication and addition.”
Session-based Recommendations with Recurrent Neural Networks (2015, neutral): “The extended version of the General Factorization Framework (GFF) (Hidasi & Tikk, 2015) is capable of using session data for recommendations.”
Sequential Recommender Systems: Challenges, Progress and Prospects (2019, methodology): “Factorization machine-based SRSs usually utilize the matrix factorization or tensor factorization to factorize the observed user-item interactions into latent factors of users and items for recommendations [14; 10].”
Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations (2016, background): “For that task [9] found that the interaction model , i.e. the sum of the user–item and user–context–item interaction to perform the best.”
Modelling Contextual Information in Session-Aware Recommender Systems with Neural Networks (2016, background): “Another possibility is to represent time dependencies between actions as a new variables in CARS models, e.g. after viewing particular items, which item was bought/seen next[3].”
Online Machine Learning in Big Data Streams (2018, methodology): “timization method for matrix factorization models, in which for a ﬁxed Q, we compute the optimal P, then for a ﬁxed P, the optimal Q, repeatedly until certain stopping criteria are met. Hidasi et al. [112, 111, 113] introduced several variants of ALS-based optimization schemes to incorporate context”
Deep Session Interest Network for Click-Through Rate Prediction (2019, methodology): “Recently, RNN-based approaches [ Hidasi et al. , 2015; Hidasi et al. , 2016; Li et al. , 2018 ] are applied into session-based recommendations to capture the order relationship within a session.”
Latent Cross: Making Use of Context in Recurrent Recommender Systems (2018, background): “Methods like factorization machines [34] and other contextual recommenders [22, 37, 48] have provided generalizations of these collaborative filtering approaches.”