Deep Matrix Factorization Models for Recommender Systems

By Hong Xue, Xinyu Dai, Jianbing Zhang, Shujian Huang, Jiajun Chen. 2017

995 citations recorded by the source corpus.

Recommender systems usually make personalized recommendation with user-item interaction ratings, implicit feedback and auxiliary information. Matrix factorization is the basic idea to predict a personalized ranking over a set of items for an individual user with the similarities among users and items. In this paper, we propose a novel matrix factorization model with neural network architecture. Firstly, we construct a user-item matrix with explicit ratings and non-preference implicit feedback. With this matrix as the input, we present a deep structure learning architecture to learn a common low dimensional space for the representations of users and items. Secondly, we design a new loss function based on binary cross entropy, in which we consider both explicit ratings and implicit feedback for a better optimization. The experimental results show the effectiveness of both our proposed model and the loss function. On several benchmark datasets, our model outperformed other state-of-the-art methods. We also conduct extensive experiments to evaluate the performance within different experimental settings.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Information Systems

Citations in the corpus

DELF: A Dual-Embedding based Deep Latent Factor Model for Recommendation (2018, result): “- DMF [Xue et al. , 2017].”
Multi-Interest Network with Dynamic Routing for Recommendation at Tmall (2019, background): “rial applications proposed by [7, 31], various types of deep models have gained significant attention. Neural Collaborative Filtering (NCF) [11], DeepFM [9] and Deep Matrix Factorization Models (DMF) [27] construct a neural network composed of several MLPs to model the interaction between users and ”
Controllable Multi-Interest Framework for Recommendation (2020, neutral): “DeepMatrix Factorization (DMF) [55] uses a deep structure learning architecture to learn a common low dimensional space for the representations of users and items based on explicit ratings and non-preference implicit feedback.”
Cross-Domain Recommendation: Challenges, Progress, and Prospects (2021, background): “…2007 ] , bayesian personalised ranking [ Rendle et al. , 2009 ] , neural collaborative ﬁltering [ He et al. , 2017 ] and deep matrix factorisation [ Xue et al. , 2017 ] ) and graphic models [ Zhu et al. , 2020; Liu et al. , 2020b ] ) to obtain user/item embeddings, and then transferring these…”
LARA: Attribute-to-feature Adversarial Learning for New-item Recommendation (2020, methodology): “Traditionally, collaborative filtering approaches, e.g. , matrix factorization based methods [19, 31, 39] and k-nearest neighbor based methods [1, 26], have been proposed by computing the similarity Zhaochun Ren and Meng Liu are corresponding authors.”
A General Cross-Domain Recommendation Framework via Bayesian Neural Network (2018, background): “- DeepMF: it is a novel matrix factorization model with neural network architecture [5].”
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time (2023, background): “Near-neighbor Search is a well-studied problem with wide applications in recommendation system (Xue et al., 2017; Hall & Attenberg, 2015), question answering (Boytsov et al., 2016; Seo et al., 2019; Chang et al., 2020) and natural language processing (Bengio et al., 2003; Lee et al., 2016).”
Deep Learning Based Recommender System (2017, background): “unobserved instances. Follow-up work [112, 134] proposed using pairwise ranking loss to enhance the performance. He et al. [92, 166] extended the NCF model to cross-domain recommendations. Xue et al. [184] and Zhang et al. [195] showed that the one-hot identi•er can be replaced with columns or rows ”
Implicit Regularization in Deep Matrix Factorization (2019, background): “[50] Hong-Jian Xue, Xinyu Dai, Jianbing Zhang, Shujian Huang, and Jiajun Chen.”
Interest-aware Message-Passing GCN for Recommendation (2021, background): “Among them, Collaborative filtering (CF) based models [1, 15, 20, 38, 41] have made substantial progress in learning user and item representations by modeling historical user-item interactions.”
Deep Item-based Collaborative Filtering for Top-N Recommendation (2018, methodology): “Note that another way to represent target item is to base on the users that have interacted with it (as used in the deepmatrix factorizationmodel [44]), which is arguablymore informative but costly.”
NPA: Neural News Recommendation with Personalized Attention (2019, result): “results validate the effectiveness of our approach. 2.2 Neural Recommender Systems In recent years, deep learning techniques have been widely used in recommender systems [31]. For example, Xue et al. [37] proposed to use multi-layer neural networks to learn the latent factors of users and items in m”
RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms (2020, background): “le 6: Implemented models in our library RecBole. Category Model Reference General recommendation Popularity - ItemKNN Deshpande and Karypis (2004) BPR Rendle et al. (2009) NeuMF He et al. (2017b) DMF Xue et al. (2017) NAIS He et al. (2018b) NGCF Wang et al. (2019e) GCMC van den Berg et al. (2017) Li”