Filters








17,762 Hits in 3.8 sec

A novel approach for venue recommendation using cross-domain techniques [article]

Pablo Sánchez, Alejandro Bellogín
2018 arXiv   pre-print
In this paper, we address the problem of venue recommendation from a novel perspective: applying cross-domain recommenda- tion techniques considering each city as a different domain.  ...  At the same time, cross-domain strategies have been exploited in the recommender systems literature when dealing with (very) sparse situations, such as those inherently arising when recommendations are  ...  Thus, based on the fact that there has not been an exhaustive analysis of the effect of different cross-domain strategies in venue recommendation, in this paper we analyze the effect of producing recommendations  ... 
arXiv:1809.09864v1 fatcat:mvycxz2dwvaive24zd7cgu2fvy

Fuzzy AHP and TOPSIS in Cross Domain Collaboration Recommendation with Fuzzy Visualization Representation

Maslina Zolkepli, Dept. of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, 43400 UPM Serdang, Selangor, Malaysia, Teh Noranis Mohd. Aris
2020 International Journal of Machine Learning and Computing  
Existing cross-domain recommendation tackles the problem of sparsity, scalability, cold-start and serendipity issues found in single-domain, therefore the combination of fuzzy AHP and TOPSIS with visualization  ...  The establishment of the cross domain recommendation will set a stage for efficient preparation for researchers who are interested to venture into other domains to increase their research competency.  ...  Another cross domain recommender system [5] transfers knowledge from the source rating matrix to help increase the prediction accuracy of the recommender system on the target rating matrix to ensure  ... 
doi:10.18178/ijmlc.2020.10.6.1000 fatcat:ddzbaq7rhfbhhns5uo2t34okom

Fuzzy AHP and TOPSIS in Cross Domain Collaboration Recommendation with Fuzzy Visualization Representation

Maslina Zolkepli, Dept. of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, 43400 UPM Serdang, Selangor, Malaysia, Teh Noranis Mohd. Aris
2019 International Journal of Machine Learning and Computing  
Existing cross-domain recommendation tackles the problem of sparsity, scalability, cold-start and serendipity issues found in single-domain, therefore the combination of fuzzy AHP and TOPSIS with visualization  ...  The establishment of the cross domain recommendation will set a stage for efficient preparation for researchers who are interested to venture into other domains to increase their research competency.  ...  Another cross domain recommender system [5] transfers knowledge from the source rating matrix to help increase the prediction accuracy of the recommender system on the target rating matrix to ensure  ... 
doi:10.18178/ijmlc.2019.9.6.882 fatcat:the7vnmnsvc7tddly3ugkqebpe

A Survey on Cross-domain Recommendation: Taxonomies, Methods, and Future Directions [article]

Tianzi Zang, Yanmin Zhu, Haobing Liu, Ruohan Zhang, Jiadi Yu
2021 arXiv   pre-print
The core idea of CDR is to leverage information collected from other domains to alleviate the two problems in one domain.  ...  In this survey paper, we first proposed a two-level taxonomy of cross-domain recommendation which classifies different recommendation scenarios and recommendation tasks.  ...  DATASETS FOR CROSS-DOMAIN RECOMMENDATION In this section, we introduce datasets used in cross-domain recommendation.  ... 
arXiv:2108.03357v1 fatcat:sitcklnxibafjomlq77rqvboia

Fluorescence resonance energy transfer microscopy as demonstrated by measuring the activation of the serine/threonine kinase Akt

Joshua A Broussard, Benjamin Rappaz, Donna J Webb, Claire M Brown
2013 Nature Protocols  
This protocol describes procedures for performing fluorescence resonance energy transfer (FRET) microscopy analysis by three different methods: acceptor photobleaching, sensitized emission and spectral  ...  Venus-C1 was a kind gift from A. Miyawaki (RIKEN, Japan).  ...  The intensity of CFP signal in the Venus-bleached ROI should increase Table 1 1 Unlinked CFP and Venus Yes Recommended Recommended Recommended Negative FRET control Linked CFP and Venus Recommended  ... 
doi:10.1038/nprot.2012.147 pmid:23306460 pmcid:PMC3756929 fatcat:6qld5ibsurha3hwhiv6ntp44oa

Cross-Domain Recommendation via Clustering on Multi-Layer Graphs

Aleksandr Farseev, Ivan Samborskii, Andrey Filchenkov, Tat-Seng Chua
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
In addition, we suggest a new approach for automatic construction of inter-network relationship graph based on the data, which eliminates the necessity of having pre-defined domain knowledge.  ...  Taking into account these two aspects, we introduce a novel cross-network collaborative recommendation framework C 3 R, which utilizes both individual and group knowledge, while being trained on data from  ...  Aiming to bridge these two research gaps, in this study, we focus on the problem of recommendation across data sources (also known as cross-domain recommendation) based on multi-view social media data.  ... 
doi:10.1145/3077136.3080774 dblp:conf/sigir/FarseevSFC17 fatcat:oq6h6njzmffj7lhzub2nsfor6a

On the effects of aggregation strategies for different groups of users in venue recommendation

Pablo Sánchez, Alejandro Bellogín
2021 Information Processing & Management  
data available in different domains.  ...  In this paper, we address the problem of venue recommendation from a novel perspective: we propose two strategies to select a set of candidate cities in order to use their information when performing recommendations  ...  Transfer (or cross-domain) learning is one of these valuable techniques that allow us to use external or additional information, mainly to improve the performance in the target domain (Lu et al., 2015  ... 
doi:10.1016/j.ipm.2021.102609 fatcat:5kdcze476zhx3eke7kij6stcui

Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling [article]

Simon Keizer, Verena Rieser
2018 arXiv   pre-print
However, despite recent progress in domain adaptation, their reliance on in-domain data still limits their cross-domain scalability.  ...  We present our multi-dimensional, statistical dialogue management framework, in which transferable conversational skills can be learnt by separating out domain-independent dimensions of communication and  ...  venue to recommend or which slot to ask about).  ... 
arXiv:1804.00146v1 fatcat:xdojv2w52jc47g6zitenneejze

Transfer Learning via Relational Type Matching

Raksha Kumaraswamy, Phillip Odom, Kristian Kersting, David Leake, Sriraam Natarajan
2015 2015 IEEE International Conference on Data Mining  
First, our approach automatically identifies predicates in the target domain that are similar in their relational structure to predicates in the source domain.  ...  Transfer learning is typically performed between problem instances within the same domain. We consider the problem of transferring across domains.  ...  Any opinions, findings, and conclusion or recommendations expressed in this material are those of the authors and do not necessarily reflect the view of the DARPA, ARO, AFRL, or the US government.  ... 
doi:10.1109/icdm.2015.138 dblp:conf/icdm/KumaraswamyOKLN15 fatcat:hcqgbbakk5gprng2gm4jfqnyw4

Hierarchy-Dependent Cross-Platform Multi-View Feature Learning for Venue Category Prediction [article]

Shuqiang Jiang and Weiqing Min and Shuhuan Mei
2018 arXiv   pre-print
HCM-FL includes two major components, namely Cross-Platform Transfer Deep Learning (CPTDL) and Multi-View Feature Learning with the Hierarchical Venue Structure (MVFL-HVS).  ...  In this work, we focus on visual venue category prediction, which can facilitate various applications for location-based service and personalization.  ...  Cross-Platform Transfer Deep Learning (CPTDL) As shown in Fig. 2(a) , we adopt the VGG-16 deep network [29] as the basic architecture in CPTDL.  ... 
arXiv:1810.09833v1 fatcat:7jd5ne3nsfdrrgao3hyptkxkcy

CATN: Cross-Domain Recommendation for Cold-Start Users via Aspect Transfer Network [article]

Cheng Zhao, Chenliang Li, Rong Xiao, Hongbo Deng, Aixin Sun
2020 arXiv   pre-print
How to effectively transfer users' preferences based on their interactions from one domain to the other relevant domain, is the key issue in cross-domain recommendation.  ...  To this end, we propose a cross-domain recommendation framework via aspect transfer network for cold-start users (named CATN).  ...  In this paper, we propose a cross-domain recommendation framework for cold-start users via aspect transfer network, named CATN.  ... 
arXiv:2005.10549v1 fatcat:pmgzfsaeozgp7cjjzoz2exh7gy

Towards Handling Unconstrained User Preferences in Dialogue [article]

Suraj Pandey, Svetlana Stoyanchev, Rama Doddipatla
2021 arXiv   pre-print
We use the annotated dataset to train and evaluate snippet relevance classifiers, as a proxy to evaluating recommendation accuracy.  ...  A user input to a schema-driven dialogue information navigation system, such as venue search, is typically constrained by the underlying database which restricts the user to specify a predefined set of  ...  The model trained on in-domain ResQS dataset achieves F1 of 0.824 and outperforms all unsupervised and transfer learning models.  ... 
arXiv:2109.08650v1 fatcat:rmzz732o2rdx3egsk4d4xp7w44

Bio-Inspired Design for Additive Manufacturing - Case Study: Microtiter Plate

Helena Hashemi Farzaneh, Ferdinand Angele, Markus Zimmermann
2019 Proceedings of the International Conference on Engineering Design  
Here, the venus' flower basket, a deep-sea sponge, can serve as a model. It has a hierarchical structure of silicate needles whose elements are abstracted for bio-inspired transfer.  ...  We apply bio-inspired design on the design of a microtiter plate manufactured by stereolithography, whose dimensional accuracy is impaired by warpage.  ...  ACKNOWLEDGEMENTS The bio-inspired prototype of a microtiter plate was based on the analysis of an initial prototype from the IDAGMED project. We therefore want to thank our project partner, Prof.  ... 
doi:10.1017/dsi.2019.32 fatcat:se3b7epk7nek7gu625c7ibpimy

PrivNet: Safeguarding Private Attributes in Transfer Learning for Recommendation [article]

Guangneng Hu, Qiang Yang
2020 arXiv   pre-print
Existing research focuses on the recommendation performance of the target domain while ignores the privacy leakage of the source domain.  ...  Transfer learning is an effective technique to improve a target recommender system with the knowledge from a source domain.  ...  ., "Findings of ACL: EMNLP 2020", which makes this paper indexed in the ACL anthology. The work was supported by Hong Kong CERG projects 16209715/16244616, and Hong Kong PhD Fellowship Scheme.  ... 
arXiv:2010.08187v1 fatcat:pvqennwzmvf5jie6ts2fqqbif4

SocialRec: A Context-aware Recommendation Framework with Explicit Sentiment Analysis

Rizwana Irfan, Osman Khalid, Muhammad U. S. Khan, Faisal Rehman, Atta Ur Rehman Khan, Raheel Nawaz
2019 IEEE Access  
In recent years, recommendation systems have seen significant evolution in the field of knowledge engineering.  ...  Usually, the recommendation systems match users' preferences based on the star ratings provided by the users for various products.  ...  Shu et al. proposed a weakly-shared Deep Transfer Network (DTN) to translate cross-domain information from web texts domain to image domain [42] .  ... 
doi:10.1109/access.2019.2932500 fatcat:tnlp3rdcnva37og7wnzbm7lee4
« Previous Showing results 1 — 15 out of 17,762 results