Filters








110,169 Hits in 3.1 sec

Learning to Recommend Accurate and Diverse Items

Peizhe Cheng, Shuaiqiang Wang, Jun Ma, Jiankai Sun, Hui Xiong
2017 Proceedings of the 26th International Conference on World Wide Web - WWW '17  
In particular, we regard each user as a training instance, and heuristically choose a subset of accurate and diverse items as groundtruth for each user.  ...  In this study, we investigate diversified recommendation problem by supervised learning, seeking significant improvement in diversity while maintaining accuracy.  ...  Technology Program (J15LN56), the National Science Foundation of United States under grant CCF-1645599 and IIS-1550302.  ... 
doi:10.1145/3038912.3052585 dblp:conf/www/ChengWMSX17 fatcat:7rlsg54qcjdknirmn3gmuu52vi

DGCN: Diversified Recommendation with Graph Convolutional Networks [article]

Yu Zheng, Chen Gao, Liang Chen, Depeng Jin, Yong Li
2021 arXiv   pre-print
Diversity, a crucial factor which measures the dissimilarity among the recommended items, received rather little scrutiny.  ...  We propose to perform rebalanced neighbor discovering, category-boosted negative sampling and adversarial learning on top of GCN. We conduct extensive experiments on real-world datasets.  ...  We hope the classifier to predict the category of the item from the item embedding as accurate as possible, and expect the recommendation model to generate item embeddings which best fool the classifier  ... 
arXiv:2108.06952v1 fatcat:sdbwxnsndvedvos5tiksaqaria

Customer Satisfaction of Recommender System: Examining Accuracy and Diversity in Several Types of Recommendation Approaches

Jae-Kyeong Kim, Il-Young Choi, Qinglong Li
2021 Sustainability  
To this end, we develop several recommender systems and measure their ability to deliver accurate and diverse recommendations and their ability to generate customer satisfaction with diverse data sets.  ...  Research on recommender systems has consistently suggested that customer satisfaction will be highest when the recommendation algorithm is accurate and recommends a diversity of items.  ...  Data Availability Statement: The data is available on https://grouplens.org/datasets/moviele ns/1m/, and http://jmcauley.ucsd.edu/data/amazon/.  ... 
doi:10.3390/su13116165 fatcat:plyrizeec5hndcjnkq7l52gr6q

A TV Program Recommender Framework

Na Chang, Mhd Irvan, Takao Terano
2013 Procedia Computer Science  
In addition, we also address several issues, such as accuracy, diversity, novelty, explanation and group recommendations, which are important in building a TV program recommender system.  ...  The proposed framework could be used to help designers/developers to build TV program recommender systems/engines for smart TV.  ...  Diversity Diversity refers to how different the items in the recommendation list are with respect to each other.  ... 
doi:10.1016/j.procs.2013.09.136 fatcat:dj2jdwrsjzecjnba4a2zfcb26m

Improved Neighborhood Search for Collaborative Filtering

Yeounoh Chung, Noo-ri Kim, Chang-yong Park, Jee-Hyong Lee
2018 International Journal of Fuzzy Logic and Intelligent Systems  
k-Nearest Neighbor (k-NN) and other user-based collaborative filtering (CF) algorithms have gained popularity because of the simplicity of their algorithms and performance.  ...  As the performance of such algorithms largely depends on neighborhood selection, it is important to select the most suitable neighborhood for each active user.  ...  Similar to Item Coverage, SU yields the most diverse recommendation lists, and then SCE, PE and CE follow.  ... 
doi:10.5391/ijfis.2018.18.1.29 fatcat:kcp3bhjenjekvfxvun5vjmkyxu

The Era of Intelligent Recommendation: Editorial on Intelligent Recommendation with Advanced AI and Learning

Shoujin Wang, Gabriella Pasi, Liang Hu, Longbing Cao
2020 IEEE Intelligent Systems  
Sydney & IT IS OUR pleasure to share with you this special issue on intelligent recommendation with advanced artificial intelligence (AI) and learning, which includes eight articles published in the September  ...  Second, we express our sincere gratitude to the IS team led by Professor Venkatramanan Subrahmanian for their support and help to ensure the timely publication of this issue.  ...  to complement user-item interactions for more accurate item recommendations.  ... 
doi:10.1109/mis.2020.3026430 fatcat:4myxztm6bzexlc6z7fffddnnk4

A Multi-Period Product Recommender System in Online Food Market based on Recurrent Neural Networks

Lee, Choi, Moon, Kim
2020 Sustainability  
Recommendation periods are segmented as various time-steps, and the proposed RNN-based recommender system can recommend items by multiple periods in a time sequence.  ...  In this research, we suggest a multi-period product recommender system, which can learn customers' purchasing order and customers' repetitive purchase pattern.  ...  . diversity(L1, L2, N) = | 2 − 1| (1) L1 and L2 are the recommended list and N is the number of recommended items.  ... 
doi:10.3390/su12030969 fatcat:6ycfzoaq6vd5joinvnn5r62vam

CauseRec: Counterfactual User Sequence Synthesis for Sequential Recommendation [article]

Shengyu Zhang, Dong Yao, Zhou Zhao, Tat-seng Chua, Fei Wu
2021 arXiv   pre-print
In this paper, we propose to learn accurate and robust user representations, which are required to be less sensitive to (attack on) noisy behaviors and trust more on the indispensable ones, by modeling  ...  The results demonstrate that the proposed CauseRec outperforms state-of-the-art sequential recommenders by learning accurate and robust user representations.  ...  To this end, learning accurate and robust users' user representations is essential for recommender systems.  ... 
arXiv:2109.05261v1 fatcat:ml4l2scfvfgh5lbdbh7r6blawq

Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation [article]

Yong Liu, Yinan Zhang, Qiong Wu, Chunyan Miao, Lizhen Cui, Binqiang Zhao, Yin Zhao, Lu Guan
2019 arXiv   pre-print
More specifically, we adopt a Determinantal Point Process (DPP) model to generate diverse, while relevant item recommendations.  ...  In this paper, we propose a novel recommendation model, named Diversity-promoting Deep Reinforcement Learning (D^2RL), which encourages the diversity of recommendation results in interaction recommendations  ...  A good interactive recommender system should be able to learn from the simulated user behaviours and make accurate while diverse recommendations.  ... 
arXiv:1903.07826v1 fatcat:s5nlfafmvjhmlct5gar2qkcrc4

A Joint Optimization Approach for Personalized Recommendation Diversification [chapter]

Xiaojie Wang, Jianzhong Qi, Kotagiri Ramamohanarao, Yu Sun, Bo Li, Rui Zhang
2018 Lecture Notes in Computer Science  
To provide the proposed algorithm with informative training labels and effectively evaluate recommendation diversity, we also propose a new personalized diversity measure.  ...  In recommendation systems, items of interest are often classified into categories such as genres of movies.  ...  The two components are collaborated by a joint optimization method to recommend items as accurately as possible (accurate rating prediction) and make an item list as personalized diverse as possible (personalized  ... 
doi:10.1007/978-3-319-93040-4_47 fatcat:ggwhtjqzazfqblct4l5t7woqdm

A Survey of Long-Tail Item Recommendation Methods

Jing Qin, Danfeng Hong
2021 Wireless Communications and Mobile Computing  
The long-tail item recommendation method not only considers the recommendation of short-head items but also considers recommending more long-tail items to users, thus improving the coverage and diversity  ...  of the research on long-tail item recommendation methods (from clustering-based, which began in 2008, to deep learning-based methods, which began in 2020) and the future directions associated with this  ...  Acknowledgments The author would like to thank the authors of all the references.  ... 
doi:10.1155/2021/7536316 fatcat:3in4tt3ntng6lew6gkvysz3rsi

A News Recommender System Considering Temporal Dynamics and Diversity [article]

Shaina Raza
2021 arXiv   pre-print
Our system should be able to: (i) accommodate the dynamics in reader behavior; and (ii) consider both accuracy and diversity in the design of the recommendation model.  ...  Our news recommender system can also work for unprofiled, anonymous and short-term readers, by leveraging the rich side information of the news items and by including the implicit feedback in our model  ...  , in order to have a more complete view of temporal dynamics; (ii) to exploit the rich side information from the news items to learn more accurate item and user representations; and (iii) to include diversity  ... 
arXiv:2103.12537v1 fatcat:7c4yojhp35asdhugtobwgwfcau

Modeling and Counteracting Exposure Bias in Recommender Systems [article]

Sami Khenissi, Olfa Nasraoui
2020 arXiv   pre-print
Our results show that recommender systems are biased and depend on the prior exposure of the user. We also show that the studied bias iteratively decreases diversity in the output recommendations.  ...  This mutual influence can lead to closed-loop interactions that may cause unknown biases which can be exacerbated after several iterations of machine learning predictions and user feedback.  ...  When the model fails to learn all of the users' diverse interests, it can keep providing the same types of recommendations again and again. This can also cause polarization [5] .  ... 
arXiv:2001.04832v1 fatcat:4tcc56lcrjflhjbibjknxljdv4

MARS: Memory Attention-Aware Recommender System [article]

Lei Zheng, Chun-Ta Lu, Lifang He, Sihong Xie, Vahid Noroozi, He Huang, Philip S. Yu
2018 arXiv   pre-print
MARS utilizes a memory component and a novel attentional mechanism to learn deep adaptive user representations. Trained in an end-to-end fashion, MARS adaptively summarizes users' interests.  ...  We also demonstrate that MARS has a great interpretability to explain its recommendation results, which is important in many recommendation scenarios.  ...  In contrast, MARS learns item features and users' attention in an end-to-end fashion. Therefore, compared with them, MARS achieves better item features and more accurate attention of users.  ... 
arXiv:1805.07037v1 fatcat:yojbwa52indpll7d2bchlvmp7a

On discovering non-obvious recommendations

Panagiotis Adamopoulos
2014 Proceedings of the 7th ACM international conference on Web search and data mining - WSDM '14  
We contribute to existing helpful but less explored recommendation strategies and propose new approaches targeting to more useful recommendations for both users and businesses.  ...  systems, based on classical metrics of dispersion and diversity as well as some newly proposed metrics.  ...  In addition, RSes should provide personalized recommendations from a wide range of items and enable the users to find relevant items that are hard to discover.  ... 
doi:10.1145/2556195.2556204 dblp:conf/wsdm/Adamopoulos14 fatcat:57euabzoyne3xodu42rcipvbku
« Previous Showing results 1 — 15 out of 110,169 results