Dual-Embedding based Deep Latent Factor Models for Recommendation

2021 ◽  
Vol 15 (5) ◽  
pp. 1-24
Author(s):  
Weiyu Cheng ◽  
Yanyan Shen ◽  
Linpeng Huang ◽  
Yanmin Zhu
Keyword(s):  
Collaborative Filtering ◽  
State Of The Art ◽  
Factor Models ◽  
Superior Performance ◽  
Implicit Feedback ◽  
The Novel ◽  
Latent Factor ◽  
Latent Factor Models ◽  
Real World Datasets

Among various recommendation methods, latent factor models are usually considered to be state-of-the-art techniques, which aim to learn user and item embeddings for predicting user-item preferences. When applying latent factor models to the recommendation with implicit feedback, the quality of embeddings always suffers from inadequate positive feedback and noisy negative feedback. Inspired by the idea of NSVD that represents users based on their interacted items, this article proposes a dual-embedding based deep latent factor method for recommendation with implicit feedback. In addition to learning a primitive embedding for a user (resp. item), we represent each user (resp. item) with an additional embedding from the perspective of the interacted items (resp. users) and propose attentive neural methods to discriminate the importance of interacted users/items for dual-embedding learning. We design two dual-embedding based deep latent factor models, DELF and DESEQ, for pure collaborative filtering and temporal collaborative filtering (i.e., sequential recommendation), respectively. The novel attempt of the proposed models is to capture each user-item interaction with four deep representations that are subtly fused for preference prediction. We conducted extensive experiments on four real-world datasets. The results verify the effectiveness of user/item dual embeddings and the superior performance of our methods on item recommendation.

scholarly journals DELF: A Dual-Embedding based Deep Latent Factor Model for Recommendation

2018 ◽  
Author(s):  
Weiyu Cheng ◽  
Yanyan Shen ◽  
Yanmin Zhu ◽  
Linpeng Huang
Keyword(s):  
Network Architecture ◽  
Factor Model ◽  
Factor Models ◽  
Superior Performance ◽  
Implicit Feedback ◽  
Latent Factor ◽  
Latent Factor Model ◽  
Latent Factor Models ◽  
Real World Datasets

Among various recommendation methods, latent factor models are usually considered to be state-of-the-art techniques, which aim to learn user and item embeddings for predicting user-item preferences. When applying latent factor models to recommendation with implicit feedback, the quality of embeddings always suffers from inadequate positive feedback and noisy negative feedback. Inspired by the idea of NSVD that represents users based on their interacted items, this paper proposes a dual-embedding based deep latent factor model named DELF for recommendation with implicit feedback. In addition to learning a single embedding for a user (resp. item), we represent each user (resp. item) with an additional embedding from the perspective of the interacted items (resp. users). We employ an attentive neural method to discriminate the importance of interacted users/items for dual-embedding learning. We further introduce a neural network architecture to incorporate dual embeddings for recommendation. A novel attempt of DELF is to model each user-item interaction with four deep representations that are subtly fused for preference prediction. We conducted extensive experiments on real-world datasets. The results verify the effectiveness of user/item dual embeddings and the superior performance of DELF on item recommendation.

scholarly journals Aspect-Level Deep Collaborative Filtering via Heterogeneous Information Networks

2018 ◽  
Author(s):  
Xiaotian Han ◽  
Chuan Shi ◽  
Senzhang Wang ◽  
Philip S. Yu ◽  
Li Song
Keyword(s):  
Neural Network ◽  
Collaborative Filtering ◽  
Factor Models ◽  
Neural Network Models ◽  
Latent Factors ◽  
Latent Factor ◽  
Heterogeneous Information ◽  
Heterogeneous Information Networks ◽  
Latent Features ◽  
Latent Factor Models

Latent factor models have been widely used for recommendation. Most existing latent factor models mainly utilize the rating information between users and items, although some recently extended models add some auxiliary information to learn a unified latent factor between users and items.  The unified latent factor only represents the latent features of users and items from the aspect of purchase history. However, the latent features of users and items may stem from different aspects, e.g., the brand-aspect and category-aspect of items. In this paper, we propose a Neural network based Aspect-level Collaborative Filtering model (NeuACF) to exploit different aspect latent factors. Through modelling rich objects and relations in recommender system as a heterogeneous information network, NeuACF first extracts different aspect-level similarity matrices of users and items through different meta-paths and then feeds an elaborately designed deep neural network with these matrices to learn aspect-level latent factors. Finally, the aspect-level latent factors are effectively fused with an attention mechanism for the top-N recommendation. Extensive experiments on three real datasets show that NeuACF significantly outperforms both existing latent factor models and recent neural network models.

scholarly journals A music recommendation algorithm based on clustering and latent factor model

2020 ◽  
Vol 309 ◽  
pp. 03009
Author(s):  
Yingjie Jin ◽  
Chunyan Han
Keyword(s):  
Collaborative Filtering ◽  
Large Scale ◽  
User Preference ◽  
Implicit Feedback ◽  
Music Recommendation ◽  
Recommendation Algorithm ◽  
Latent Factor ◽  
Latent Factor Models ◽  
Feedback Data ◽  
Preference Matrix

The collaborative filtering recommendation algorithm is a technique for predicting items that a user may be interested in based on user history preferences. In the recommendation process of music data, it is often difficult to score music and the display score data for music is less, resulting in data sparseness. Meanwhile, implicit feedback data is more widely distributed than display score data, and relatively easy to collect, but implicit feedback data training efficiency is relatively low, usually lacking negative feedback. In order to effectively solve the above problems, we propose a music recommendation algorithm combining clustering and latent factor models. First, the user-music play record data is processed to generate a user-music matrix. The data is then analyzed using a latent factor probability model on the resulting matrix to obtain a user preference matrix U and a musical feature matrix V. On this basis, we use two K- means algorithms to perform user clustering and music clustering on two matrices. Finally, for the user preference matrix and the commodity feature matrix that complete the clustering, a user-based collaborative filtering algorithm is used for prediction. The experimental results show that the algorithm can reduce the running cost of large-scale data and improve the recommendation effect.

AN OPTIMAL SCALING FRAMEWORK FOR COLLABORATIVE FILTERING RECOMMENDATION SYSTEMS

2012 ◽  
Vol 21 (06) ◽  
pp. 1250033
Author(s):  
MANOLIS G. VOZALIS ◽  
ANGELOS I. MARKOS ◽  
KONSTANTINOS G. MARGARITIS
Keyword(s):  
Missing Data ◽  
Collaborative Filtering ◽  
Principal Component ◽  
Factor Models ◽  
Optimal Scaling ◽  
Low Rank ◽  
Data Sets ◽  
Low Rank Approximation ◽  
Latent Factor ◽  
Latent Factor Models

Collaborative Filtering (CF) is a popular technique employed by Recommender Systems, a term used to describe intelligent methods that generate personalized recommendations. Some of the most efficient approaches to CF are based on latent factor models and nearest neighbor methods, and have received considerable attention in recent literature. Latent factor models can tackle some fundamental challenges of CF, such as data sparsity and scalability. In this work, we present an optimal scaling framework to address these problems using Categorical Principal Component Analysis (CatPCA) for the low-rank approximation of the user-item ratings matrix, followed by a neighborhood formation step. CatPCA is a versatile technique that utilizes an optimal scaling process where original data are transformed so that their overall variance is maximized. We considered both smooth and non-smooth transformations for the observed variables (items), such as numeric, (spline) ordinal, (spline) nominal and multiple nominal. The method was extended to handle missing data and incorporate differential weighting for items. Experiments were executed on three data sets of different sparsity and size, MovieLens 100k, 1M and Jester, aiming to evaluate the aforementioned options in terms of accuracy. A combined approach with a multiple nominal transformation and a "passive" missing data strategy clearly outperformed the other tested options for all three data sets. The results are comparable with those reported for single methods in the CF literature.

scholarly journals On Inductive Abilities of Latent Factor Models for Relational Learning

2019 ◽  
Vol 64 ◽  
pp. 21-53
Author(s):  
Théo Trouillon ◽  
Eric Gaussier ◽  
Christopher R. Dance ◽  
Guillaume Bouchard
Keyword(s):  
State Of The Art ◽  
Factor Models ◽  
Binary Relations ◽  
Latent Factor ◽  
Research Directions ◽  
Atomic Properties ◽  
Relational Knowledge ◽  
Latent Factor Models ◽  
New Research ◽  
Experimental Survey

Latent factor models are increasingly popular for modeling multi-relational knowledge graphs. By their vectorial nature, it is not only hard to interpret why this class of models works so well, but also to understand where they fail and how they might be improved. We conduct an experimental survey of state-of-the-art models, not towards a purely comparative end, but as a means to get insight about their inductive abilities. To assess the strengths and weaknesses of each model, we create simple tasks that exhibit first, atomic properties of binary relations, and then, common inter-relational inference through synthetic genealogies. Based on these experimental results, we propose new research directions to improve on existing models.

scholarly journals VAEGAN: A Collaborative Filtering Framework based on Adversarial Variational Autoencoders

2019 ◽  
Author(s):  
Xianwen Yu ◽  
Xiaoning Zhang ◽  
Yang Cao ◽  
Min Xia
Keyword(s):  
Collaborative Filtering ◽  
State Of The Art ◽  
High Accuracy ◽  
Generative Adversarial Networks ◽  
Implicit Feedback ◽  
Inference Model ◽  
Penalty Term ◽  
Adversarial Networks ◽  
Adversarial Training ◽  
Real World Datasets

Recently, Variational Autoencoders (VAEs) have been successfully applied to collaborative filtering for implicit feedback. However, the performance of the resulting model depends a lot on the expressiveness of the inference model and the latent representation is often too constrained to be expressive enough to capture the true posterior distribution. In this paper, a novel framework named VAEGAN is proposed to address the above issue. In VAEGAN, we first introduce Adversarial Variational Bayes (AVB) to train Variational Autoencoders with arbitrarily expressive inference model. By utilizing Generative Adversarial Networks (GANs) for implicit variational inference, the inference model provides better approximation to the posterior and maximum-likelihood assignment. Then the performance of our model is further improved by introducing an auxiliary discriminative network using adversarial training to achieve high accuracy in recommendation. Furthermore, contractive loss is added to the classical reconstruction cost function as a penalty term to yield robust features and improve the generalization performance. Finally, we show that the performance of our proposed VAEGAN significantly outperforms state-of-the-art baselines on several real-world datasets.

scholarly journals A Graphical and Attentional Framework for Dual-Target Cross-Domain Recommendation

2020 ◽  
Author(s):  
Feng Zhu ◽  
Yan Wang ◽  
Chaochao Chen ◽  
Guanfeng Liu ◽  
Xiaolin Zheng
Keyword(s):  
State Of The Art ◽  
The Novel ◽  
Target Domain ◽  
Cross Domain ◽  
Single Target ◽  
Recommendation Accuracy ◽  
Real World Datasets ◽  
Content Information ◽  
Dual Target

The conventional single-target Cross-Domain Recommendation (CDR) only improves the recommendation accuracy on a target domain with the help of a source domain (with relatively richer information). In contrast, the novel dual-target CDR has been proposed to improve the recommendation accuracies on both domains simultaneously. However, dual-target CDR faces two new challenges: (1) how to generate more representative user and item embeddings, and (2) how to effectively optimize the user/item embeddings on each domain. To address these challenges, in this paper, we propose a graphical and attentional framework, called GA-DTCDR. In GA-DTCDR, we first construct two separate heterogeneous graphs based on the rating and content information from two domains to generate more representative user and item embeddings. Then, we propose an element-wise attention mechanism to effectively combine the embeddings of common users learned from both domains. Both steps significantly enhance the quality of user and item embeddings and thus improve the recommendation accuracy on each domain. Extensive experiments conducted on four real-world datasets demonstrate that GA-DTCDR significantly outperforms the state-of-the-art approaches.

scholarly journals SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback

2020 ◽  
Vol 34 (04) ◽  
pp. 6127-6136
Author(s):  
Chao Wang ◽  
Hengshu Zhu ◽  
Chen Zhu ◽  
Chuan Qin ◽  
Hui Xiong
Keyword(s):  
Bayesian Approach ◽  
Posterior Probability ◽  
State Of The Art ◽  
User Preferences ◽  
Implicit Feedback ◽  
Pairwise Preference ◽  
Entire List ◽  
Collaborative Ranking ◽  
Real World Datasets ◽  
Made In

The recent development of online recommender systems has a focus on collaborative ranking from implicit feedback, such as user clicks and purchases. Different from explicit ratings, which reflect graded user preferences, the implicit feedback only generates positive and unobserved labels. While considerable efforts have been made in this direction, the well-known pairwise and listwise approaches have still been limited by various challenges. Specifically, for the pairwise approaches, the assumption of independent pairwise preference is not always held in practice. Also, the listwise approaches cannot efficiently accommodate “ties” due to the precondition of the entire list permutation. To this end, in this paper, we propose a novel setwise Bayesian approach for collaborative ranking, namely SetRank, to inherently accommodate the characteristics of implicit feedback in recommender system. Specifically, SetRank aims at maximizing the posterior probability of novel setwise preference comparisons and can be implemented with matrix factorization and neural networks. Meanwhile, we also present the theoretical analysis of SetRank to show that the bound of excess risk can be proportional to √M/N, where M and N are the numbers of items and users, respectively. Finally, extensive experiments on four real-world datasets clearly validate the superiority of SetRank compared with various state-of-the-art baselines.

scholarly journals Label Distribution for Learning with Noisy Labels

2020 ◽  
Author(s):  
Yun-Peng Liu ◽  
Ning Xu ◽  
Yu Zhang ◽  
Xin Geng
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Confidence Estimation ◽  
Novel Method ◽  
Real World Datasets ◽  
Label Distribution ◽  
Noisy Labels

The performances of deep neural networks (DNNs) crucially rely on the quality of labeling. In some situations, labels are easily corrupted, and therefore some labels become noisy labels. Thus, designing algorithms that deal with noisy labels is of great importance for learning robust DNNs. However, it is difficult to distinguish between clean labels and noisy labels, which becomes the bottleneck of many methods. To address the problem, this paper proposes a novel method named Label Distribution based Confidence Estimation (LDCE). LDCE estimates the confidence of the observed labels based on label distribution. Then, the boundary between clean labels and noisy labels becomes clear according to confidence scores. To verify the effectiveness of the method, LDCE is combined with the existing learning algorithm to train robust DNNs. Experiments on both synthetic and real-world datasets substantiate the superiority of the proposed algorithm against state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document