Attentive Contextual Denoising Autoencoder for Recommendation

Jhamb, Yogesh; Ebesu, Travis; Fang, Yi

doi:10.1145/3234944.3234956

Cited by 43 publications

(24 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a different strategy comparing to the interaction-shared layer commonly used by a considerable number of DNN-based recommenders. Jhamb et al (2018) propose a DAE architecture to encode contextual information via an attention mechanism. The Attentive Contextual Denoising Autoencoder (ACDA) adopts context weights for users and items for further incorporating them to user rating history to learn a unified latent representation suitable for recommendation ranking tasks.…”

Section: Synthesis Of Main Primary Studiesmentioning

confidence: 99%

Deep learning techniques for recommender systems based on collaborative filtering

2020

View full text Add to dashboard Cite

In the Big Data Era, recommender systems perform a fundamental role in data management and information filtering. In this context, Collaborative Filtering (CF) persists as one of the most prominent strategies to effectively deal with large datasets and is capable of offering users interesting content in a recommendation fashion. Nevertheless, it is well-known CF recommenders suffer from data sparsity, mainly in cold-start scenarios, substantially reducing the quality of recommendations. In the vast literature about the aforementioned topic, there are numerous solutions, in which the state-of-the-art contributions are, in some sense, conditioned or associated with traditional CF methods such as Matrix Factorization (MF), that is, they rely on linear optimization procedures to model users and items into low-dimensional embeddings. To overcome the aforementioned challenges, there has been an increasing number of studies exploring deep learning techniques in the CF context for latent factor modelling. In this research, authors conduct a systematic review focusing on state-of-theart literature on deep learning techniques applied in collaborative filtering recommendation, and also featuring primary studies related to mitigating the cold start problem. Additionally, authors considered the diverse non-linear modelling strategies to deal with rating data and side information, the combination of deep learning techniques with traditional CF-based linear methods, and an overview of the most used public datasets and evaluation metrics concerning CF scenarios.

show abstract

Section: Synthesis Of Main Primary Studiesmentioning

confidence: 99%

Deep learning techniques for recommender systems based on collaborative filtering

2020

View full text Add to dashboard Cite

show abstract

“…First, the sigmoid function constrains the ability of each neuron to be in (0,1), which may reduce the efficiency of the models; and it is obvious that it tends to experience saturation, where neurons discontinue the learning process where the output is close to either 1 or 0. Second, tanh is a more enhanced candidate and has been extensively used [12,48,49]. It can only reduce the Sigmoid problem to some level; hence it is a rescaled variant of Sigmoid (tanh(x=2) = 25-007(x) -1).…”

Section: B Multi-layer Perceptronmentioning

confidence: 99%

“…DNN techniques have already been effectively implemented and have accomplished favorable results in several research areas, such as Computer Vision (CV), speech recognition, and Natural Language Processing (NLP) [10], [11]. Research findings have shown that the artificial neural network has a strong ability to learn latent and N-dimensional characteristics from homogeneous and heterogeneous information and to achieve accurate results [12], [13]. Among them, the Embedding based (EB) method and Multi-Layer Perceptron (MLP) have been extensively applied in Recommender Systems lately.…”

Section: Introductionmentioning

confidence: 99%

Deep Edu: A Deep Neural Collaborative Filtering for Educational Services Recommendation

et al. 2020

View full text Add to dashboard Cite

In the modern world, people face an explosion of information and difficulty to find the right choice of their interest. Nowadays, people show interest in online shopping to meet their demands increasingly. For researchers and students, finding and buying the desired books from online shops is very tedious work. Recently Recommender System is an excellent tool to deal with such problems, but the Recommender System is suffering from multiple problems such as data sparsity, coldstart, and inaccuracy. To address these problems, we propose Deep Edu a novel Deep Neural Collaborative Filtering for educational services recommendation. A Deep Edu architecture consists of three parts of a Deep Neural Network model (such as input layer, a multilayered perceptron, and an output layer). The Deep Edu provides the following contributions: first, the users' identifier and books identifier features are mapped into N-dimensional dense embedding vectors, second, the Multi-Layer-Perceptron (MLP) takes the N-dimensional and non-linear features. To increase the performance of Deep Edu in all metrics, we proposed the advance Loss function. Equipped with the following, Deep Edu not only capable of learning the Ndimensional and non-linear interactions between users' identifier and books identifier, but moreover, it also considerably mitigates the cold-start, data sparsity, and inaccuracy problem. Over significant experiments performed on real-world good books dataset, the results show that Deep Edu's recommendation performance obviously outperforms existing Educational services recommendation methods.

show abstract

“…Attention has also been successfully applied in different recommendation tasks [38]- [43]. For example, MPCN [40] is a multi-pointer co-attention network that takes user and item reviews as input, and then extracts the most informative reviews that contribute more in predictions.…”

Section: Attention Mechanismmentioning

confidence: 99%

CATA++: A Collaborative Dual Attentive Autoencoder Method for Recommending Scientific Articles

Alfarhood

Cheng

2020

IEEE Access

View full text Add to dashboard Cite

Matrix Factorization (MF) method is widely popular for personalized recommendations. However, the natural data sparsity problem limits its performance, where users generally only interact with a small fraction of available items. Accordingly, several hybrid models have been proposed recently to optimize MF performance by incorporating additional contextual information in the MF's learning process. Although these models improved recommendation quality, there are two primary aspects for further enhancements: (1) multiple models focus only on some portion of the available contextual information and neglect other portions, and (2) learning the feature space of the contextual information needs to be further improved. Therefore, we introduce a Collaborative Dual Attentive Autoencoder (CATA++) method that utilizes an item's content and learns its latent space via two parallel autoencoders. We employ the attention mechanism in the middle of our autoencoders to capture the most significant segments of contextual information, which leads to a better representation of the items in the latent space. Extensive experiments on three scientific-article datasets have shown that our dual-process learning strategy has significantly improved MF performance in comparison with other state-of-the-art MF-based models using various experimental evaluations. The source code of our method is available at: https://github.com/jianlin-cheng/CATA.

show abstract

Attentive Contextual Denoising Autoencoder for Recommendation

Cited by 43 publications

References 23 publications

Deep learning techniques for recommender systems based on collaborative filtering

Deep learning techniques for recommender systems based on collaborative filtering

Deep Edu: A Deep Neural Collaborative Filtering for Educational Services Recommendation

CATA++: A Collaborative Dual Attentive Autoencoder Method for Recommending Scientific Articles

Contact Info

Product

Resources

About