22,810 Hits in 4.7 sec

Recommendation in heterogeneous information network via dual similarity regularization

Jing Zheng, Jian Liu, Chuan Shi, Fuzhen Zhuang, Jingzhi Li, Bin Wu
2016 International Journal of Data Science and Analytics  
The social recommendation methods tend to leverage social relations among users obtained from social network to alleviate data sparsity and cold-start problems in recommender systems.  ...  With the dual similarity regularization, we further propose an optimization function to integrate the similarity information of users and items under different semantic meta-paths, and a gradient descend  ...  [26] integrates heterogeneous information via flexible regularization of users and items for better recommendation.  ... 
doi:10.1007/s41060-016-0031-0 dblp:journals/ijdsa/ZhengLSZLW17 fatcat:o2wce62dyrhxxmd7xbbqpfaq5m

Dual Similarity Regularization for Recommendation [chapter]

Jing Zheng, Jian Liu, Chuan Shi, Fuzhen Zhuang, Jingzhi Li, Bin Wu
2016 Lecture Notes in Computer Science  
The social recommendation methods usually employ simple similarity information of users as social regularization on users.  ...  In order to overcome the shortcomings of social regularization, we propose a new dual similarity regularization to impose the constraint on users and items with high and low similarities simultaneously  ...  However, rich similarity information on users and items can be generated in a heterogeneous information network.  ... 
doi:10.1007/978-3-319-31750-2_43 fatcat:hxcbsvtufjfabpgiqfcf43pccy

Integrating Heterogeneous Information via Flexible Regularization Framework for Recommendation [article]

Chuan Shi, Jian Liu, Fuzhen Zhuang, Philip S. Yu, Bin Wu
2015 arXiv   pre-print
In this paper, we organize objects and relations in recommendation system as a heterogeneous information network, and introduce meta path based similarity measure to evaluate the similarity of users or  ...  Furthermore, a matrix factorization based dual regularization framework SimMF is proposed to flexibly integrate different types of information through adopting the similarity of users and items as regularization  ...  CONCLUSION In this paper, we organize the objects and relations in recommendation system as a heterogeneous information network, and designed a unified and flexible matrix factorization based dual regularization  ... 
arXiv:1511.03759v1 fatcat:nlx76g3revdeviz6r2o7brvpye

Heterogeneous Information Network Embedding for Recommendation [article]

Chuan Shi, Binbin Hu, Wayne Xin Zhao, Philip S. Yu
2017 arXiv   pre-print
Due to the flexibility in modelling data heterogeneity, heterogeneous information network (HIN) has been adopted to characterize complex and heterogeneous auxiliary data in recommender systems, called  ...  In this paper, we propose a novel heterogeneous network embedding based approach for HIN based recommendation, called HERec.  ...  . • DSR [12] : It is a MF based recommendation method with dual similarity regularization, which imposes the constraint on users and items with high and low similarities simultaneously.  ... 
arXiv:1711.10730v1 fatcat:g3z5i6gnd5aljeyscma2cco64m

RDF-to-Text Generation with Graph-augmented Structural Neural Encoders

Hanning Gao, Lingfei Wu, Po Hu, Fangli Xu
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
To address these issues, we propose to jointly learn local and global structure information via combining two new graph-augmented structural neural encoders (i.e., a bidirectional graph encoder and a bidirectional  ...  However, none of these methods can explicitly model both local and global structure information between and within the triples.  ...  In contrast, the novel dual-target CDR has been recently proposed to improve the recommendation accuracies on both richer and sparser domains simultaneously by making good use of the information or knowledge  ... 
doi:10.24963/ijcai.2020/415 dblp:conf/ijcai/ZhuWCLZ20 fatcat:bfw4nsudpjbvlnbpjdyssk3mla

Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Peng He, Paul Weng, Han Gao, Guihai Chen
2019 The World Wide Web Conference on - WWW '19  
Social recommendation leverages social information to solve data sparsity and cold-start problems in traditional collaborative filtering methods.  ...  To relax this strong assumption, in this paper, we propose dual graph attention networks to collaboratively learn representations for two-fold social effects, where one is modeled by a user-specific attention  ...  We are the rst to use GAT for social recommendation task, and our new architecture, dual GATs, can capture social information in both user and item networks.  ... 
doi:10.1145/3308558.3313442 dblp:conf/www/WuZGHWGC19 fatcat:2ciwch3szng63lobo5ug2ac55a

Recent Advances in Heterogeneous Relation Learning for Recommendation [article]

Chao Huang
2021 arXiv   pre-print
We discuss the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information.  ...  Recommender systems have played a critical role in many web applications to meet user's personalized interests and alleviate the information overload.  ...  (2) How to perform the information fusion based on the extracted knowledge via automatic machine learning frameworks, and endow the user preference modeling paradigms with heterogeneous context incorporation  ... 
arXiv:2110.03455v1 fatcat:fskj4qdsibfnxefklazdli3tgu

Self-supervised Learning for Large-scale Item Recommendations [article]

Tiansheng Yao, Xinyang Yi, Derek Zhiyuan Cheng, Felix Yu, Ting Chen, Aditya Menon, Lichan Hong, Ed H. Chi, Steve Tjoa, Jieqi Kang, Evan Ettinger
2021 arXiv   pre-print
Large scale recommender models find most relevant items from huge catalogs, and they play a critical role in modern search and recommendation systems.  ...  To model the input space with large-vocab categorical features, a typical recommender model learns a joint embedding space through neural networks for both queries and items from user feedback data.  ...  The goal is to recommend highly similar apps given a seed app. This is also formulated as an item-to-item recommendation problem via a multi-class classification loss.  ... 
arXiv:2007.12865v4 fatcat:euu7phtharckdbwki3cfceqmq4

DDTCDR: Deep Dual Transfer Cross Domain Recommendation [article]

Pan Li, Alexander Tuzhilin
2019 arXiv   pre-print
To address these concerns, in this paper we propose a novel approach to cross-domain recommendations based on the mechanism of dual learning that transfers information between two related domains in an  ...  Combining with autoencoder approach to extract the latent essence of feature information, we propose Deep Dual Transfer Cross Domain Recommendation (DDTCDR) model to provide recommendations in respective  ...  and Dual Regularization [36] .  ... 
arXiv:1910.05189v1 fatcat:y5mqqv3gebgqbgakxk4qzubgmq

Social Role Identification via Dual Uncertainty Minimization Regularization

Yu Cheng, Ankit Agrawal, Alok Choudhary, Huan Liu, Tao Zhang
2014 2014 IEEE International Conference on Data Mining  
Realizing the natural setting of social nodes associated with dual view information, i.e., the local node characteristics and the global network influence, we present a novel model that explores graph  ...  regularization techniques and integrates such information to achieve improved prediction performance.  ...  Motivated by multi-view learning idea [9] , [10] , here we propose a graph regularization based learning framework that integrates heterogeneous information.  ... 
doi:10.1109/icdm.2014.31 dblp:conf/icdm/ChengACLZ14 fatcat:xsjzh26hrrhgnpwk3rqw4wfnxm

A Unified Framework for Cross-Domain and Cross-System Recommendations [article]

Feng Zhu, Yan Wang, Jun Zhou, Chaochao Chen, Longfei Li, Guanfeng Liu
2021 arXiv   pre-print
In this paper, we focus on three new scenarios, i.e., Dual-Target CDR (DTCDR), Multi-Target CDR (MTCDR), and CDR+CSR, and aim to improve the recommendation accuracy in all datasets simultaneously for all  ...  In GA, we first construct separate heterogeneous graphs to generate more representative user and item embeddings.  ...  Then, we leverage rating and content information of each domain to construct a heterogeneous graph, representing user-item interaction relationships, user-user similarity relationships, and itemitem similarity  ... 
arXiv:2108.07976v1 fatcat:gfie4f5b4ncuvotz7wiqlhaice

A Comprehensive Survey on Community Detection with Deep Learning [article]

Xing Su, Shan Xue, Fanzhen Liu, Jia Wu, Jian Yang, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Di Jin, Quan Z. Sheng, Philip S. Yu
2021 arXiv   pre-print
in handling high dimensional network data.  ...  A community reveals the features and connections of its members that are different from those in other communities in a network. Detecting communities is of great significance in network analysis.  ...  To imbalanced communities, Dual-Regularized Graph Convolutional Networks (DR-GCN) [95] utilizes a conditional GAN into the dual-regularized GCN model, i.e., a latent distribution alignment regularization  ... 
arXiv:2105.12584v2 fatcat:matipshxnzcdloygrcrwx2sxr4

ICDE conference 2015 detailed author index

2015 2015 IEEE 31st International Conference on Data Engineering  
, and Visualizing Geotagged Microblogs Muthulingam, Sujatha 1253 Oracle Database In-Memory: A Dual Format In-Memory Database Mylopoulos, John 1538 Goals in Social Media, Information Retrieval  ...  Users in Social Networks with Limited Information Vijayarajendran, Priya 1400 Advanced Analytics on SAP HANA: Churn Risk Scoring Using Call Network Analysis Voigt, Hannes 1460 Enjoy FRDM -Play with a  ... 
doi:10.1109/icde.2015.7113260 fatcat:ep7pomkm55f45j33tkpoc5asim

Hybrid social media network

Dong Liu, Guangnan Ye, Ching-Ting Chen, Shuicheng Yan, Shih-Fu Chang
2012 Proceedings of the 20th ACM international conference on Multimedia - MM '12  
However, there are many heterogeneous entities and relations in such networks, making it difficult to fully represent and exploit the diverse array of information.  ...  The network can be used to generate personalized information recommendation in response to specific targets of interests, e.g., personalized multimedia albums, target advertisement and friend/topic recommendation  ...  The heterogeneous information network [10, 12] in the data mining community also attempts to model the relations between heterogeneous entities.  ... 
doi:10.1145/2393347.2393438 dblp:conf/mm/LiuYCYC12 fatcat:gncqk24wsjewpiqi5og5rqgp6q

DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction [article]

Ruijie Wang, Zijie Huang, Shengzhong Liu, Huajie Shao, Dongxin Liu, Jinyang Li, Tianshi Wang, Dachun Sun, Shuochao Yao, Tarek Abdelzaher
2021 arXiv   pre-print
similar interests.  ...  Inferring user interests from diffusion data lies the foundation of diffusion prediction, because users often forward the information in which they are interested or the information from those who share  ...  ACKNOWLEDGEMENTS This work was funded in part by DARPA under award W911NF-17-C-0099, and by DoD Basic Research Office under award HQ00342110002.  ... 
arXiv:2106.03251v1 fatcat:forh47cfcnhb3dlk44wq4mqr2u
« Previous Showing results 1 — 15 out of 22,810 results