Open AccessJournal Article
SVDFeature: a toolkit for feature-based collaborative filtering
TLDR
SVDFeature is designed to efficiently solve the feature-based matrix factorization and is capable of both rate prediction and collaborative ranking, and is carefully designed for efficient training on large-scale data set.Abstract:
In this paper we introduce SVDFeature, a machine learning toolkit for feature-based collaborative filtering. SVDFeature is designed to efficiently solve the feature-based matrix factorization. The feature-based setting allows us to build factorization models incorporating side information such as temporal dynamics, neighborhood relationship, and hierarchical information. The toolkit is capable of both rate prediction and collaborative ranking, and is carefully designed for efficient training on large-scale data set. Using this toolkit, we built solutions to win KDD Cup for two consecutive years.read more
Citations
More filters
Proceedings ArticleDOI
Collaborative Deep Learning for Recommender Systems
TL;DR: Wang et al. as discussed by the authors proposed a hierarchical Bayesian model called collaborative deep learning (CDL), which jointly performs deep representation learning for the content information and collaborative filtering for the ratings (feedback) matrix.
Journal ArticleDOI
Heterogeneous Information Network Embedding for Recommendation
TL;DR: A novel heterogeneous network embedding based approach for HIN based recommendation, called HERec is proposed, which shows the capability of the HERec model for the cold-start problem, and reveals that the transformed embedding information from HINs can improve the recommendation performance.
Proceedings ArticleDOI
Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention
TL;DR: A novel attention mechanism in CF is introduced to address the challenging item- and component-level implicit feedback in multimedia recommendation, dubbed Attentive Collaborative Filtering (ACF), which significantly outperforms state-of-the-art CF methods.
Proceedings ArticleDOI
xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
TL;DR: A novel Compressed Interaction Network (CIN), which aims to generate feature interactions in an explicit fashion and at the vector-wise level and is named eXtreme Deep Factorization Machine (xDeepFM), which is able to learn certain bounded-degree feature interactions explicitly and can learn arbitrary low- and high-order feature interactions implicitly.
Journal ArticleDOI
Collaborative filtering and deep learning based recommendation system for cold start items
TL;DR: Two recommendation models to solve the CCS and ICS problems for new items are proposed, which are based on a framework of tightly coupled CF approach and deep learning neural network.
References
More filters
Combining Factorization Model and Additive Forest for Collaborative Followee Recommendation
Tianqi Chen,Linpeng Tang,Qin Liu,Diyi Yang,Saining Xie,Xuezhi Cao,Chunyang Wu,Enpeng Yao,Zhengyang Liu,Zhansheng Jiang,Cheng Chen,Weihao Kong,Yong Yu +12 more
TL;DR: The modeling approach is able to utilize various side information provided by the challenge dataset, and thus alleviates the cold-start problem, and the new temporal dynamics model the authors have proposed using an additive forest can automatically adjust the splitting time points to model popularity evolution more accurately.
Rating Prediction with Informative Ensemble of Multi-Resolution Dynamic Models.
TL;DR: An informative ensemble framework is designed, which considers additional meta features when making predictions for a particular pair of user and item and adopts time series based parameterizations and models user/item drifting behaviors at multiple temporal resolutions.
Proceedings Article
Rating prediction with informative ensemble of multi-resolution dynamic models
TL;DR: In this article, a class of time-aware matrix/tensor factorization models is proposed to capture the rich temporal dynamics within the data set, which adopts time series based parameterizations and models user/item drifting behaviors at multiple temporal resolutions.