22,173 Hits in 6.6 sec

QoS Prediction for Neighbor Selection via Deep Transfer Collaborative Filtering in Video Streaming P2P Networks

Wenming Ma, Qian Zhang, Chunxiao Mu, Meng Zhang
2019 International Journal of Digital Multimedia Broadcasting  
In this paper, we proposed a novel neural collaborative filtering method based on transfer learning, which can evaluate the QoS with few historical data by evaluating the other different QoS properties  ...  Each client in the P2P streaming network should select a group of neighbors by evaluating the QoS of the other nodes.  ...  Recently, some studies have proposed some deep learning-based collaborative filtering models. Two impressive technologies are Google's Wide & Deep [48] and Microsoft's Deep Crossing [49] .  ... 
doi:10.1155/2019/1326831 fatcat:tipayxrpzrcqriavyvcnuiuwo4

JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendation [article]

Zhiwei Liu, Lei Zheng, Jiawei Zhang, Jiayu Han, Philip S. Yu
2019 arXiv   pre-print
Cross-domain recommendation can alleviate the data sparsity problem in recommender systems.  ...  Extensive experiments on $24$ Amazon rating datasets show the effectiveness of JSCN in the cross-domain recommendation, with $9.2\%$ improvement on recall and $36.4\%$ improvement on MAP compared with  ...  Even if a common user only exists in part of all the domains, the information can be shared across different domains, as the effect of collaborative filtering.  ... 
arXiv:1910.08219v1 fatcat:3wyulfy6ffexlo6zac3o2gbetm

Leveraging Virtual and Real Person for Unsupervised Person Re-identification [article]

Fengxiang Yang, Zhun Zhong, Zhiming Luo, Sheng Lian, Shaozi Li
2018 arXiv   pre-print
For training of deep re-ID model, we divide it into three steps: 1) pre-training a coarse re-ID model by using virtual data; 2) collaborative filtering based positive pair mining from the real data; and  ...  Although recent deep re-ID methods have achieved great improvement, it is still difficult to optimize deep re-ID model without annotations in training data.  ...  N p is number of identities in virtual person dataset. The cross-entropy loss function is used to train the coarse re-ID model. C.  ... 
arXiv:1811.02074v1 fatcat:al26lwojuvbkbi2dviyls4zaye

CoNet: Collaborative Cross Networks for Cross-Domain Recommendation [article]

Guangneng Hu, Yu Zhang, Qiang Yang
2018 arXiv   pre-print
In contrast to the matrix factorization based cross-domain techniques, our method is deep transfer learning, which can learn complex user-item interaction relationships.  ...  We assume that hidden layers in two base networks are connected by cross mappings, leading to the collaborative cross networks (CoNet).  ...  Conclusions We proposed a novel approach to perform knowledge transfer learning for cross-domain recommendation via collaborative cross networks (CoNet).  ... 
arXiv:1804.06769v2 fatcat:g5t3u3vxjbahbj7gpx2mwteh54

Cross-domain Recommendation via Deep Domain Adaptation [article]

Heishiro Kanagawa, Hayato Kobayashi, Nobuyuki Shimizu, Yukihiro Tagami, Taiji Suzuki
2018 arXiv   pre-print
JAPAN and show that our approach outperforms several baseline methods including a cross-domain collaborative filtering method.  ...  With this formulation, the problem is reduced to a domain adaptation setting, in which a classifier trained in the source domain is adapted to the target domain.  ...  CONCLUSIONS AND DISCUSSIONS In this paper, we studied a problem of cross-domain recommendation in which we cannot expect common users or items and presented a new deep learning approach using domain adaptation  ... 
arXiv:1803.03018v1 fatcat:pp4l375psfhite2ia7d2clhpna

A Multifaceted Model for Cross Domain Recommendation Systems [chapter]

Jianxun Lian, Fuzheng Zhang, Xing Xie, Guangzhong Sun
2017 Lecture Notes in Computer Science  
In this paper, we introduce a Multifaceted Cross-Domain Recommendation System (MCDRS) which incorporates two different types of collaborative filtering for cross domain RSs.  ...  In order to utilize as much knowledge as possible, we propose a unified factorization framework to combine both CF and content-based filtering for cross domain learning.  ...  MCDRS-significantly outperforms STLCF and MV-DNN due to its utilization of both collaborative filtering and content-based filtering in the cross domain situation.  ... 
doi:10.1007/978-3-319-63558-3_27 fatcat:kzlfi5iz5fc57hmri44z6d22ci

Semi-supervised Collaborative Filtering by Text-enhanced Domain Adaptation [article]

Wenhui Yu and Xiao Lin and Junfeng Ge and Wenwu Ou and Zheng Qin
2020 arXiv   pre-print
By domain adaptation, the distribution pattern in the source domain is transferred to the target domain.  ...  To solve these difficulties, we regard the problem of recommendation on sparse implicit feedbacks as a semi-supervised learning task, and explore domain adaption to solve it.  ...  to encode user preferences in Collaborative Filtering (CF) models.  ... 
arXiv:2007.07085v1 fatcat:otwwodkmibdfhg3bozfxfk2rte

MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Prediction [article]

Wentao Ouyang, Xiuwu Zhang, Lei Zhao, Jinmei Luo, Yu Zhang, Heng Zou, Zhaojie Liu, Yanlong Du
2020 arXiv   pre-print
In this paper, we address this problem and leverage auxiliary data from a source domain to improve the CTR prediction performance of a target domain.  ...  Nevertheless, ads are usually displayed with natural content, which offers an opportunity for cross-domain CTR prediction.  ...  Cross-Domain Methods. (1) CCCFNet. Cross-domain Content-boosted Collaborative Filtering Network [15] .  ... 
arXiv:2008.02974v1 fatcat:lhxuowldd5apvhq5wlojgkfbkq

Structure-Attentioned Memory Network for Monocular Depth Estimation [article]

Jing Zhu, Yunxiao Shi, Mengwei Ren, Yi Fang, Kuo-Chin Lien, Junli Gu
2019 arXiv   pre-print
Recent deep learning models have been proposed to predict the depth from the image by learning the alignment of deep features between the RGB image and the depth domains.  ...  More specifically, in the SOM module, we develop a Memorable Bank of Filters (MBF) unit to learn a set of filters that memorize the structure-aware image-depth residual pattern, and also an Attention Guided  ...  Bank of Filters (MBF) and an Attention Guided Controller (AGC) for feature-level cross-modality domain adaptation. • We propose a novel end-to-end deep learning Structure-Attentioned Memory Network, which  ... 
arXiv:1909.04594v1 fatcat:3teklxde5je5roz4pteysdimtq

Cross-domain Human Parsing via Adversarial Feature and Label Adaptation [article]

Si Liu, Yao Sun, Defa Zhu, Guanghui Ren, Yu Chen, Jiashi Feng and Jizhong Han
2018 arXiv   pre-print
To this end, we propose a novel and efficient cross-domain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities  ...  Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences.  ...  Model Learning and Inference Training details of the integrated cross-domain human parsing framework are summarized in Algorithm 1.  ... 
arXiv:1801.01260v2 fatcat:urndeykaffb2ddhomz64uudmyu

A Dictionary Approach to Domain-Invariant Learning in Deep Networks [article]

Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
2020 arXiv   pre-print
In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN).  ...  domain adaptation.  ...  For supervised learning, the loss function is the cross-entropy for each domain.  ... 
arXiv:1909.11285v2 fatcat:4ucz7cnm4nbtvbu2z7xbgpszyy

Latent User Linking for Collaborative Cross Domain Recommendation [article]

Sapumal Ahangama, Danny Chiang-Choon Poo
2019 arXiv   pre-print
In this publication, we propose a deep learning method for cross-domain recommender systems through the linking of cross-domain user latent representations as a form of knowledge transfer across domains  ...  With the widespread adoption of information systems, recommender systems are widely used for better user experience. Collaborative filtering is a popular approach in implementing recommender systems.  ...   MLP [8]: The model is a recent state of the art deep neural network model for collaborative filtering.  ... 
arXiv:1908.06583v1 fatcat:curd5j6arfasfmzfzk5fbsfw4u

Unravelling Small Sample Size Problems in the Deep Learning World [article]

Rohit Keshari, Soumyadeep Ghosh, Saheb Chhabra, Mayank Vatsa, Richa Singh
2020 arXiv   pre-print
In this paper, we first present a review of deep learning algorithms for small sample size problems in which the algorithms are segregated according to the space in which they operate, i.e. input space  ...  The growth and success of deep learning approaches can be attributed to two major factors: availability of hardware resources and availability of large number of training samples.  ...  [63] have utilized two losses (softmax cross-entropy loss, and domain confusion loss) to train the network on target dataset. Moreover, in place of confusion loss, Long et al.  ... 
arXiv:2008.03522v1 fatcat:nigmkyma6rahvfhylcml3xmmxq

Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification [article]

Fengxiang Yang, Ke Li, Zhun Zhong, Zhiming Luo, Xing Sun, Hao Cheng, Xiaowei Guo, Feiyue Huang, Rongrong Ji, Shaozi Li
2019 arXiv   pre-print
Although recent advances in deep learning have achieved remarkable accuracy in settled scenes, i.e., source domain, few works can generalize well on the unseen target domain.  ...  Extensive experiments show that the proposed framework can consistently benefit most clustering-based methods, and boost the state-of-the-art adaptation accuracy.  ...  With the rapid evolution of deep learning models, the accuracy of person re-ID has been greatly boosted in the public datasets.  ... 
arXiv:1912.01349v1 fatcat:ttbn62j5mvacnosn3lnab3loby

Transfer Meets Hybrid: A Synthetic Approach for Cross-Domain Collaborative Filtering with Text [article]

Guangneng Hu, Yu Zhang, Qiang Yang
2019 arXiv   pre-print
We propose a novel neural model to smoothly enable Transfer Meeting Hybrid (TMH) methods for cross-domain recommendation with unstructured text in an end-to-end manner.  ...  On two real-world datasets, TMH shows better performance in terms of three ranking metrics by comparing with various baselines.  ...  To the best of our knowledge, TMH is the first deep model that transfers cross-domain knowledge for recommendation with unstructured text in an end-to-end learning.  ... 
arXiv:1901.07199v1 fatcat:ti7l7rv2vzca7cauwh4iidaceq
« Previous Showing results 1 — 15 out of 22,173 results