Filters








30,100 Hits in 6.5 sec

Guest editorial: web multimedia semantic inference using multi-cues

Yahong Han, Yi Yang, Xiaofang Zhou
2015 World wide web (Bussum)  
In this issue, two papers investigate cross-media distance metric learning and domain adaptation for Web multimedia semantic analysis.  ...  The paper, titled "A Cross-media Distance Metric Learning Framework based on Multi-view Correlation Mining and Matching", presents a novel cross-media distance metric learning framework based on sparse  ... 
doi:10.1007/s11280-015-0360-2 fatcat:vc4plge5qvg7hfmza3dffmawki

Experimental analysis on cross domain preferences association and rating prediction

Zhenhua Dong, Qian Zhao
2012 Proceedings of the 1st International Workshop on Cross Domain Knowledge Discovery in Web and Social Network Mining - CDKD '12  
Cross domain recommendation and preferences association are emerging research topics.  ...  of cross domain rating prediction based on KNN model.  ...  Conclusion and Future Work This paper analyses two specific questions in the cross-domain learning by experiment.  ... 
doi:10.1145/2351333.2351337 fatcat:jjjxcd5ozrai5gwv4irekwoely

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
CATN is devised to extract multiple aspects for each user and each item from their review documents, and learn aspect correlations across domains with an attention mechanism.  ...  To this end, we propose a cross-domain recommendation framework via aspect transfer network for cold-start users (named CATN).  ...  Cross-Domain Aspect Correlation Learning Now, we have abstract aspect features A u and A i for user u and item i respectively.  ... 
arXiv:2005.10549v1 fatcat:pmgzfsaeozgp7cjjzoz2exh7gy

Knowledge-aware Neural Collective Matrix Factorization for Cross-domain Recommendation [article]

Li Zhang, Yan Ge, Jun Ma, Jianmo Ni, Haiping Lu
2022 arXiv   pre-print
Then, we maximize the mutual information between item embeddings learned from the KG and user-item matrix to establish cross-domain relationships for better CDR.  ...  Cross-domain recommendation (CDR) can help customers find more satisfying items in different domains.  ...  for better cross-domain recommendation performance.  ... 
arXiv:2206.13255v1 fatcat:vsz7mlb3x5byxow7dxnxpv2cti

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

Tianzi Zang, Yanmin Zhu, Haobing Liu, Ruohan Zhang, Jiadi Yu
2022 arXiv   pre-print
Over the last decade, many efforts have been engaged for cross-domain recommendation. Recently, with the development of deep learning and neural networks, a large number of methods have emerged.  ...  In this survey paper, we first proposed a two-level taxonomy of cross-domain recommendation which classifies different recommendation scenarios and recommendation tasks.  ...  They proposed a cross-domain recommendation approach with semantic correlations in tagging systems (SCT).  ... 
arXiv:2108.03357v2 fatcat:ywwh44x3pfbnbesy5ojogg4hyy

Cross-Domain Recommender Systems [chapter]

Iván Cantador, Ignacio Fernández-Tobías, Shlomo Berkovsky, Paolo Cremonesi
2015 Recommender Systems Handbook  
and sparsity problems in a target domain, or enabling personalized crossselling recommendations for items from multiple domains.  ...  Cross-domain recommender systems, thus, aim to generate or enhance recommendations in a target domain by exploiting knowledge from source domains.  ...  Overall, about 14% of the papers use semantic-based user preferences.  ... 
doi:10.1007/978-1-4899-7637-6_27 fatcat:4kregbpxajbnxmg6xywfmm22ki

A Novel Embedding Model for Relation Prediction in Recommendation Systems

Yu ZHAO, Sheng GAO, Patrick GALLINARI, Jun GUO
2017 IEICE transactions on information and systems  
and item prediction simultaneously for recommendation systems, by learning the latent semantic representation of the users, items and ratings.  ...  In addition, we apply the proposed model to cross-domain recommendation, which is able to realize recommendation generation in multiple domains.  ...  Acknowledgments Thanks to Spyridoula G. for proofreading my manuscripts.  ... 
doi:10.1587/transinf.2016edp7421 fatcat:7r3n4e7btrajvflqnsr7rubpoi

Cross-domain User Preference Learning for Cold-start Recommendation [article]

Huiling Zhou, Jie Liu, Zhikang Li, Jin Yu, Hongxia Yang
2021 arXiv   pre-print
Cross-domain cold-start recommendation is an increasingly emerging issue for recommender systems.  ...  Now the method is serving online for the cross-domain cold micro-video recommendation.  ...  CONCLUSION In this paper, we proposed a unified framework for cross-domain cold-start recommendation in real world.  ... 
arXiv:2112.03667v1 fatcat:fvg2amg5qber7encbsxgosxgtu

Towards Universal Sequence Representation Learning for Recommender Systems [article]

Yupeng Hou, Shanlei Mu, Wayne Xin Zhao, Yaliang Li, Bolin Ding, Ji-Rong Wen
2022 arXiv   pre-print
For learning universal sequence representations, we introduce two contrastive pre-training tasks by sampling multi-domain negatives.  ...  For learning universal item representations, we design a lightweight item encoding architecture based on parametric whitening and mixture-of-experts enhanced adaptor.  ...  CONCLUSIONS In this paper, we propose the universal sequence representation learning approach for recommender systems, named UniSRec.  ... 
arXiv:2206.05941v1 fatcat:2vlxpd3dt5ctnosblc7nccqwdm

Cross-domain Recommendations for Personalized Semantic Services

Hla Hla Moe, Win Thanda Aung
2012 International Journal of Computer Applications Technology and Research  
This paper tends to provide cross-domain recommendations for personalized semantic services using Taxonomic CCBR, directed acyclic graph by Ford-Fulkerson algorithm and TOPSIS method.  ...  Among them, cross-domain recommendation is an emerging research topic and in this field, it is important to investigate how to manage personalization and how to consider customer's contextual features  ...  In this paper, a framework for cross-domain recommender system is proposed.  ... 
doi:10.7753/ijcatr0201.1015 fatcat:bxhjdqqmvfco3fh46kfx4cf4he

Domain-Independent Extraction of Scientific Concepts from Research Articles [chapter]

Arthur Brack, Jennifer D'Souza, Anett Hoppe, Sören Auer, Ralph Ewerth
2020 Lecture Notes in Computer Science  
Second, we present a state-of-the-art deep learning baseline. Further, we propose the active learning strategy for an optimal selection of instances from among the various domains in our data.  ...  We examine the novel task of domain-independent scientific concept extraction from abstracts of scholarly articles and present two contributions.  ...  In the future, we plan to extend and refine the concepts for certain domains.  ... 
doi:10.1007/978-3-030-45439-5_17 fatcat:mu2acaudwzgardhwnp2iozuc4a

Toward a Knowledge-based Personalised Recommender System for Mobile App Development [article]

Bilal Abu-Salih, Hamad Alsawalqah, Basima Elshqeirat, Tomayess Issa, Pornpit Wongthongtham
2020 arXiv   pre-print
This paper proposes a new recommender system framework comprising a fortified set of techniques that are designed to provide mobile app developers with a distinctive platform to browse and search for the  ...  The proposed system make use of ontology and semantic web technology as well as machine learning techniques.  ...  ; and (ii) provision of domain-based time-aware recommendations to users by means of a recommender system that incorporates domain ontology and knowledge. 5 Conclusions and Future Work This paper  ... 
arXiv:1909.03733v3 fatcat:jct7p54g6jdhxpy6cctqn6snyq

Learning Relevance of Web Resources across Domains to Make Recommendations

Julia Hoxha, Peter Mika, Roi Blanco
2013 2013 12th International Conference on Machine Learning and Applications  
We present an approach that applies Support Vector Machines for learning the relevance of resources and predicting which ones are the most relevant to recommend to a user, given that the user is currently  ...  In real-world datasets of semantically-enriched logs of user browsing behavior at multiple Web sites, we study the impact of structure in generating accurate recommendations and conduct experiments that  ...  The authors thank Pablo Castells (Universidad Autònoma de Madrid) for the helpful comments and feedback.  ... 
doi:10.1109/icmla.2013.144 dblp:conf/icmla/HoxhaMB13 fatcat:jzifeqkiwzg6lhaem6mnp44krm

Disentangled Contrastive Learning for Social Recommendation [article]

Jiahao Wu, Wenqi Fan, Jingfan Chen, Shengcai Liu, Qing Li, Ke Tang
2022 arXiv   pre-print
Most social recommendation models unify user representations for the user-item interactions (collaborative domain) and social relations (social domain).  ...  Social recommendations utilize social relations to enhance the representation learning for recommendations.  ...  Disentangled Contrastive Learning Disentangled contrastive learning consists of cross-domain contrastive learning and domain-specific contrastive learning.  ... 
arXiv:2208.08723v1 fatcat:q6jepjopzfdjdntpeaw5q7p4fy

Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation

Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis, Luc Van Gool
2021 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Furthermore, we propose an Iterative Self-Learning (ISL) training scheme, which exploits semantic pseudo-labels to provide extra supervision on the target domain.  ...  We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting.  ...  We thank Amazon Activate for EC2 credits and the anonymous reviewers for the valuable feedback and time spent.  ... 
doi:10.1109/cvpr46437.2021.00810 fatcat:yfbe7ybq75df3dwb33pvsbqagu
« Previous Showing results 1 — 15 out of 30,100 results