30,379 Hits in 4.7 sec

Multiple Interest and Fine Granularity Network for User Modeling [article]

Jiaxuan Xie, Jianxiong Wei, Qingsong Hua, Yu Zhang
2021 arXiv   pre-print
the paper, we present Multiple interest and Fine granularity Net-work (MFN), which tackle users' multiple and fine-grained interests and construct the model from both the similarity relationship and the  ...  Then a hierarchical network is applied to model the attention relation between the multiple interest vectors of different granularities and the target item.  ...  SIM [10] leverages a general search unit to get a sub user behavior And the other set of embedding E is trainable and is trained under Multiple Interest and Fine Granularity Network for User Modeling  ... 
arXiv:2112.02591v1 fatcat:zstmy7fvmbayljxf4dmqp2qd3a

Cloud Synergetic Recommendation Model for Overseas Chinese Education by Modeling Multi-Source User Metaphor Information

Zhehuang Huang
2019 International Journal of Emerging Technologies in Learning (iJET)  
Firstly, a user vector space with fine granularity representation is constructed by introducing multi-knowledge source emotional metaphor information.  ...  The model proposed in this paper has certain reference significance for overseas Chinese education and online learning model.  ...   Constructing user vector space with fine granularity representation from multiple knowledge sources such as domain interests, personal preferences and browsing history  Obtain implicit emotional and  ... 
doi:10.3991/ijet.v14i23.11105 fatcat:vnaztdlponefzioi6oh5d4lnxe

Modeling the value of information granularity in targeted advertising

Swati Rallapalli, Qiang Ma, Han Hee Song, Mario Baldi, S. Muthukrishnan, Lili Qiu
2014 Performance Evaluation Review  
This work contributes (i) a MOdel of the Value of INformation Granularity (MoVInG) that captures the impact of additional information on the revenue from targeted ads in case of uniform bidding and (ii  ...  Combining and using data from different collectors can be very useful for advertising.  ...  Challenges: Estimating the benefit of fine-grained user data is challenging due to the following reasons: (1) lack of measures for data quality that take into account different granularities for various  ... 
doi:10.1145/2627534.2627547 fatcat:qgo4ri63kbefdijb63djwmqqte

Multi-Granularity Representations of Dialog

Shikib Mehri, Maxine Eskenazi
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Analysis significantly demonstrates that multiple granularities of representation are being learned, and that multi-granularity training facilitates better transfer to downstream tasks.  ...  Neural models of dialog rely on generalized latent representations of language.  ...  MGT is expected to outperform standard ensembling, since MGT explicitly models multiple granularities and trains more diverse models.  ... 
doi:10.18653/v1/d19-1184 dblp:conf/emnlp/MehriE19 fatcat:zgtwwapngrhpvcsk46b526kycy

Impact of request dispatching granularity in geographically distributed Web systems

Mauro Andreolini, Claudia Canali, Riccardo Lancellotti
2007 Sixth IEEE International Symposium on Network Computing and Applications (NCA 2007)  
Through a real prototype, we compare dispatching mechanisms operating at various levels of granularity for different workload and network scenarios.  ...  We demonstrate that the choice of the best granularity for request dispatching strongly depends on the characteristics of the workload in terms of heterogeneity and computational requirements.  ...  We recall that a user click for a Web resource originates multiple requests for the resource template and the components, each of them may require a different generation or adaptation service.  ... 
doi:10.1109/nca.2007.28 dblp:conf/nca/AndreoliniCL07 fatcat:4mz2rp54abgaxdvvsmqfvs2iaq

WiFiMod: Transformer-based Indoor Human Mobility Modeling using Passive Sensing [article]

Amee Trivedi, Kate Silverstein, Emma Strubell, Mohit Iyyer, Prashant Shenoy
2021 arXiv   pre-print
Next, for each extracted trajectory, we identify the mobility features at multiple spatial scales, macro, and micro, to design a multi-modal embedding Transformer that predicts user mobility for several  ...  hours to an entire day across multiple spatial granularities.  ...  Our model seeks to predict the trajectory of each user while learning the correlation between the c,s,b, and l at multiple spatial granularities.  ... 
arXiv:2104.09835v3 fatcat:pg7zbyxkcrevxickb2it2ww2kq

Multi-Granularity Representations of Dialog [article]

Shikib Mehri, Maxine Eskenazi
2019 arXiv   pre-print
Analysis significantly demonstrates that multiple granularities of representation are being learned, and that multi-granularity training facilitates better transfer to downstream tasks.  ...  Neural models of dialog rely on generalized latent representations of language.  ...  Even with the dual encoder as the underlying model, MGT outperforms all previous work except for Sequential Matching Networks (SMN) and Deep Attention Matching networks (DAM) (Zhou et al., 2018) .  ... 
arXiv:1908.09890v1 fatcat:fm2pakzxkbcirfpeo5lf6iujiq

On Finding Fine-Granularity User Communities by Profile Decomposition

Seulki Lee, Minsam Ko, Keejun Han, Jae-Gil Lee
2012 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining  
Using a real data set of CiteULike, we show that our proposed algorithm can precisely distinguish multiple research interests of a user and discover communities corresponding to each interest, whereas  ...  Overall, profile decomposition enables us to find fine-granularity user communities, thus improving the accuracy of community discovery.  ...  Profile decomposition divides a user's profile into multiple sub-profiles, thus enabling us to find fine-granularity user communities.  ... 
doi:10.1109/asonam.2012.106 dblp:conf/asunam/LeeKHL12 fatcat:x7e7tltstzanxlzbswkguizp3m

Qos Mapping For Fine Granular Scalability With Base Layer Scaling

Katsuhiko Fukazawa, Masayuki Inoue, Shigetaro Iwatsu, Yoshiyuki Yashima
2006 Zenodo  
This paper uses MPEG4 FGS (Fine Granular Scalability) [9] with base layer scaling to implement application-level QoS control, because of its ability to adjust to a wide range of network channel capacities  ...  for decoderelement, and 'Gender', 'Age', 'Imagery', and 'Interest' as the user-element parameters, which are human factors as is shown in Table 1 .  ... 
doi:10.5281/zenodo.39548 fatcat:o5qhbmltyrafrapthjxupr5nae

A Multi-Granular Aggregation-Enhanced Knowledge Graph Representation for Recommendation

Xi Liu, Rui Song, Yuhang Wang, Hao Xu
2022 Information  
In this paper, we propose a new model, named A Multi-Granular Aggregation-Enhanced Knowledge Graph Representation for Recommendation (MAKR), that relieves the sparsity of the network and overcomes the  ...  nodes in the heterogeneous network into three categories—users, items, and entities, and connects the edges according to the similarity between the users and items so as to enhance the high-order connectivity  ...  Acknowledgments: The authors would like to thank all of anonymous reviewers and editors for their helpful suggestions for the improvement of this paper.  ... 
doi:10.3390/info13050229 fatcat:k4fqottd3vaoncy5r7kgdty4zi

Multidimensional Data Stream Summarization Using Extended Tilted-Time Windows

Yoann Pitarch, Anne Laurent, Marc Plantevit, Pascal Poncelet
2009 2009 International Conference on Advanced Information Networking and Applications Workshops  
Nowadays, servers register more and more log entries. Monitoring, analyzing and exctracting knowledge from networks and web servers is crucial for a lot of applications.  ...  Generaly, users consult the recent history at fine levels of granularity. Then, this need of precision decreases when the age of the data increases. To this end, we introduce precision functions.  ...  This model consists 1 in considering time at multiple levels of granularity and will be more described in Section 2.2.  ... 
doi:10.1109/waina.2009.145 dblp:conf/aina/PitarchLPP09 fatcat:jihvhyjxvvhhxhuibvnekntbee

Quantified Spectrum Sharing: Motivation, Approach, and Benefits [article]

Nilesh Khambekar, Chad Spooner, Vipin Chaudhary
2016 arXiv   pre-print
In this paper, we investigate the limitations of the existing techniques and argue for quantified approach to dynamic spectrum sharing and management.  ...  The growing demand for spectrum has spurred a need for dynamic spectrum sharing paradigm.  ...  We refer to the aggregate of RF-networks sharing a spectrum space in the time, space, and frequency dimensions within the geographical region of interest as a RF-system and such multiple RF-systems are  ... 
arXiv:1608.07854v1 fatcat:b3odcczaa5hyrmu2rohlecewvq

A Systematic Analysis of Fine-Grained Human Mobility Prediction with On-Device Contextual Data [article]

Huoran Li
2019 arXiv   pre-print
Based on a Markov model, a recurrent neural network, and a multi-modal learning method, we perform a series of experiments to investigate the predictability of different types of granularities of prediction  ...  User mobility prediction is widely considered to be helpful for various sorts of location based services on mobile devices.  ...  Researchers have already proposed a variety of prediction models based on multiple technologies, including pattern-based models [1, 2, 3] , Markovbased models [15, 6, 7] , and neural network models  ... 
arXiv:1901.10167v1 fatcat:dbzaxfq2cza67flhpvdnce4ete

Multiple Granularity Descriptors for Fine-Grained Categorization

Dequan Wang, Zhiqiang Shen, Jie Shao, Wei Zhang, Xiangyang Xue, Zheng Zhang
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
Our multiple granularity framework can be learned with the weakest supervision, requiring only image-level label and avoiding the use of labor-intensive bounding box or part annotations.  ...  The internal representations of these networks have different region of interests, allowing the construction of multi-grained descriptors that encode informative and discriminative features covering all  ...  Acknowledgements We would like to thank anonymous reviewers for helpful feedback. We would also like to thank Tianjun Xiao and Hao Ye for useful discussions.  ... 
doi:10.1109/iccv.2015.276 dblp:conf/iccv/WangSSZXZ15 fatcat:uccgg6vquzhbxoghp77y6txjvm

End-to-End service provisioning in multigranularity multidomain optical networks

Yong Zhu, A. Jukan, M. Ammar, W. Alanqar
2004 2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577)  
This network model is referred to as multisegment network model, where the notion of networking segments refers to any portion of an optical network that requires particular consideration for control,  ...  Based on the multi-segment framework, we developed routing schemes for the multi-granularity multi-domain optical networks.  ...  Among them, the definition of standard control plane architectures for network control and user-to-network and network-to-network interfaces (UNI and NNI, respectively) for inter-domain communication have  ... 
doi:10.1109/icc.2004.1312776 dblp:conf/icc/ZhuJAA04 fatcat:4svczytxwfcz7ef5icl5jbmbly
« Previous Showing results 1 — 15 out of 30,379 results