Filters








35,247 Hits in 1.4 sec

Latent Unexpected Recommendations [article]

Pan Li, Alexander Tuzhilin
2020 arXiv   pre-print
In addition, we develop a novel Latent Closure (LC) method to construct hybrid utility function and provide unexpected recommendations based on the proposed model.  ...  Previous unexpected recommendation methods only focus on the straightforward relations between current recommendations and user expectations by modeling unexpectedness in the feature space, thus resulting  ...  Unexpected Recommendation Performance To start with, we compare the recommendation performance of proposed latent unexpectedness with baseline unexpected recommendation models.  ... 
arXiv:2007.13280v1 fatcat:oxnronmcp5bm7h5sllm3axkryu

Latent Unexpected and Useful Recommendation [article]

Pan Li, Alexander Tuzhilin
2019 arXiv   pre-print
In this paper, we define unexpectedness in the latent space rather than in the feature space and develop a novel Latent Convex Hull (LCH) method to provide unexpected recommendations.  ...  Providing unexpected recommendations is an important task for recommender systems.  ...  : Can our model reach a higher coverage of the latent space compared to other unexpected recommendation models?  ... 
arXiv:1905.01546v1 fatcat:lldrp5k4vvb7zing5hdv7e2ufq

Latent Modeling of Unexpectedness for Recommendations

Pan Li, Alexander Tuzhilin
2019 ACM Conference on Recommender Systems  
In this paper, we propose to model unexpectedness in the latent space and utilize a latent convex hull structure to provide unexpected recommendations, as illustrated in Figure 1 .  ...  Unexpectedness constitutes an important factor for recommender system to improve user satisfaction and avoid filter bubble issues.  ...  In addition, the proposed approach outperforms all previous unexpected recommendation models introduced in page 3, which validates the superiority of modeling unexpectedness in the latent space over feature  ... 
dblp:conf/recsys/LiT19 fatcat:sx52bwuawranzo4vj2qqffgkqa

Robust Recommendation with Implicit Feedback via Eliminating the Effects of Unexpected Behaviors [article]

Jie Chen and Lifen Jiang and Chunmei Ma and Huazhi Sun
2021 arXiv   pre-print
Existing studies fail to model the effects of unexpected behaviors, thus achieve inferior recommendation performance.  ...  Finally, an output module is performed to eliminate the effects of unexpected behaviors and integrates all the information to make a final recommendation.  ...  In this section, we briefly review related works from three perspectives: session-based recommendation, latent factor models and a new trend in recommendation.  ... 
arXiv:2112.11023v1 fatcat:y43y6cngajcgxfztlzf7vntps4

Serendipitous Personalized Ranking for Top-N Recommendation

Qiuxia Lu, Tianqi Chen, Weinan Zhang, Diyi Yang, Yong Yu
2012 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology  
Serendipitous recommendation has benefitted both e-retailers and users. It tends to suggest items which are both unexpected and useful to users.  ...  However, due to the imbalance in observed data for popular and tail items, existing collaborative filtering methods fail to give satisfactory serendipitous recommendations.  ...  If α is too low, the model will bias towards the popular items which are lowly unexpected, thus the unexpectedness will be reduced. So in both situations, the recommendation serendipity will drop.  ... 
doi:10.1109/wi-iat.2012.135 dblp:conf/webi/LuCZYY12 fatcat:3i2olk2ztnbqdo4zncmhq4nqki

Page 200 of The Laryngoscope Vol. 71, Issue 2 [page]

1961 The Laryngoscope  
Two articles'* recommended the following procedure to detect bleeding disorders: 1.  ...  For a long time the detection of latent hemorrhagic dis- orders has been an important and controversial problem in surgery.  ... 

A serendipity-biased Deepwalk for collaborators recommendation

Zhenzhen Xu, Yuyuan Yuan, Haoran Wei, Liangtian Wan
2019 PeerJ Computer Science  
The unexpected and valuable scientific discoveries in science such as X-rays and penicillin may be attributed to serendipity.  ...  We first introduce the definition of serendipitous collaborators from three components of serendipity: relevance, unexpectedness, and value, respectively.  ...  The unexpectedness is measured as the rate of unexpected collaborators in the recommendation list.  ... 
doi:10.7717/peerj-cs.178 pmid:33816831 pmcid:PMC7924530 fatcat:n3hqtt324ffrtdxfbgynnkfrbm

Customer satisfaction modeling (CSM) in product planning according to quality function deployment (QFD) and Kano model

Hossein Vazifehdust
2011 African Journal of Business Management  
By setting forth 7 hypotheses in this research, the relationship of product performance (basic needs, performance needs, excitement needs) and the value provided for the customer (expected and unexpected  ...  In the final model obtained from this study, parameters of Indirect effect of the endogenous Latent variables measuring model, coefficient of the route variable Unexpected Value on customer between latent  ...  Kano, Model is recommended to be discussed before Danavan and Hugat (2001) and Taora (2004). research methodology after literature review.  ... 
doi:10.5897/ajbm11.1304 fatcat:uxcdahrcjzgo5nrn7tlqm4h4um

Page 367 of American Society of Civil Engineers. Collected Journals Vol. 114, Issue 3 [page]

1988 American Society of Civil Engineers. Collected Journals  
One of the unexpected soil behaviors described by the author discusses time-dependent or latent strength gains in clean sands after deep compact- ing by dynamic methods (i.e., dynamic compaction, vibro  ...  Because of the previously mentioned problems with measuring relative density in the laboratory, which are magnified in the field, the writers do not recommend such a procedure for applied design purposes  ... 

Expanding the Latent Space of StyleGAN for Real Face Editing [article]

Yin Yu, Ghasedi Kamran, Wu HsiangTao, Yang Jiaolong, Tong Xi, Fu Yun
2022 arXiv   pre-print
To successfully edit a real image, one must first convert the input image into StyleGAN's latent variables.  ...  In this paper, we present a method to expand the latent space of StyleGAN with additional content features to break down the trade-off between low-distortion and high-editability.  ...  Zoom-in recommended. using both pSp and e4e encoders, then apply editing methods on these latent codes to synthesize editing images.  ... 
arXiv:2204.12530v1 fatcat:ayaxmzj2yvdv3d66t4xaet6jyu

A Serendipity Model for News Recommendation [chapter]

M. Jenders, T. Lindhauer, G. Kasneci, R. Krestel, F. Naumann
2015 Lecture Notes in Computer Science  
Serendipitous recommendations have the characteristic of being unexpected yet fortunate and interesting to the user, and thus might yield higher user satisfaction.  ...  We propose a content-based recommendation technique with the focus on serendipity of news recommendations.  ...  In the field of music recommendation, the authors of [6] find that content-based systems are better at recommending novel items, as collaborative filtering systems are drawn to more popular items.  ... 
doi:10.1007/978-3-319-24489-1_9 fatcat:q7brpluhm5h2zd7t65ptc43yu4

Special section on recommender systems in tourism

Julia Neidhardt, Tsvi Kuflik, Wolfgang Wörndl
2018 Information Technology & Tourism  
The focus of this special section is on the specific challenges for recommender systems in tourism.  ...  The common task of classical recommender systems is to find the best (single) product for a user, but in the domain of tourism, the scenario is considerably more complex.  ...  The title of the second paper is "Estimating a latent-class user model for travel recommender systems".  ... 
doi:10.1007/s40558-018-0111-1 fatcat:5gna2rgxpnedjl5pnc5jzysflm

Page 102 of Journal of Imaging Science Vol. 1, Issue 3 [page]

1958 Journal of Imaging Science  
Abney recommended hydro- quinone as a developer in 1880 and Bogisch and Andresen recommended metol in 1891.  ...  This unexpected effect has been investigated repeatedly in other binary developing mixtures, especially by Levenson,** and various explanations of the phenomenon have been offered.  ... 

Infection in the process of organ donation

O Len Abad
2019 Revista Espanola de Quimioterapia  
In that sense, initiatives such as the Notify Library (www.notifylibrary.org) promoted by the Centro Nazionale Table 1 1 Recommended screening for latent infections in the donor Ab: antibody; Ag: antigen  ...  CAUSES OF UNEXPECTED TRANSMISSION OF INFECTION There are several causes that lead to the unexpected transmission of an infection.  ... 
pmid:31475815 pmcid:PMC6755361 fatcat:bkc5nnyx3jhencbxkcbiicfpfu

A Fuzzy Set Based Approach for Rating Bias

Mingming Li, Jiao Dai, Fuqing Zhu, Liangjun Zang, Songlin Hu, Jizhong Han
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In recommender systems, the user uncertain preference results in unexpected ratings.  ...  Introduction Matrix Factorization is one of the most famous and successful recommendation approaches, which learns the discriminative latent factors for users and items by factorizing useritem interaction  ...  Let Ri,j represent the rating of user i on item j; U ∈ R N ×K and V ∈ R M ×K be latent user and item feature matrices, with column vectors Ui and Vj representing user-specific and item-specific latent  ... 
doi:10.1609/aaai.v33i01.33019969 fatcat:4q4mxtmkzfcajaovet7pcrywau
« Previous Showing results 1 — 15 out of 35,247 results