Filters








46,187 Hits in 6.3 sec

Joint Link Prediction and Attribute Inference Using a Social-Attribute Network

Neil Zhenqiang Gong, Ameet Talwalkar, Lester Mackey, Ling Huang, Eui Chul Richard Shin, Emil Stefanov, Elaine (Runting) Shi, Dawn Song
2014 ACM Transactions on Intelligent Systems and Technology  
The effects of social influence and homophily suggest that both network structure and node attribute information should inform the tasks of link prediction and node attribute inference.  ...  [Yin et al. 2010a; 2010b] proposed an attribute-augmented social network model, which we call as Social-Attribute Network (SAN), to integrate network structure and node attributes to perform both link  ...  MODEL AND ALGORITHMS Social-Attribute Network Model Social-Attribute Network was first proposed by Yin et al. [Yin et al. 2010a; 2010b] 2 to predict links and infer attributes.  ... 
doi:10.1145/2594455 fatcat:3kvor2tzszegvdhnmoiwnyqaga

Max-margin latent feature relational models for entity-attribute networks

Fei Xia, Ning Chen, Jun Zhu, Aonan Zhang, Xiaoming Jin
2014 2014 International Joint Conference on Neural Networks (IJCNN)  
Link prediction is a fundamental task in statistical analysis of network data.  ...  This paper presents an approach to automatically learn latent features from partially observed heterogeneous networks, with a particular focus on entity-attribute networks (EANs), and making predictions  ...  ENTITY-ATTRIBUTE NETWORK To make our joint latent feature models generally applicable, we first formalize a generic class of heterogeneous networks as Entity-Attribute Networks, which include social networks  ... 
doi:10.1109/ijcnn.2014.6889508 dblp:conf/ijcnn/XiaCZZJ14 fatcat:ly2zkkrsfzacvpciaseaocd2ym

Latent Space Model for Multi-Modal Social Data

Yoon-Sik Cho, Greg Ver Steeg, Emilio Ferrara, Aram Galstyan
2016 Proceedings of the 25th International Conference on World Wide Web - WWW '16  
We validate the proposed framework on two problems: prediction of social interactions from user attributes and behaviors, and behavior prediction exploiting network information.  ...  We derive an efficient inference algorithm based on Variational Expectation Maximization that has a computational cost linear in the size of the network, thus making it feasible to analyze massive social  ...  and social networks, and avoid the fragmentation of the joint latent space.  ... 
doi:10.1145/2872427.2883031 dblp:conf/www/ChoSFG16 fatcat:jter6ht6gfenxhlxvn5fnw4qxy

Privacy Inference Attack Against Users in Online Social Networks: A Literature Review

Yangheran Piao, Kai Ye, Xiaohui Cui
2021 IEEE Access  
Social relationship inference and attribute inference are two basic attacks on users' privacy in social networks. This is the first systematic review of privacy inference attacks in social networks.  ...  A large amount of privacy information can be inferred from the content and social traces published by users, which leads to the rise of privacy inference technology for users in social networks.  ...  Y Tian et al. proposed a private attribute inference method based on a graph convolutional neural network, which used visible user-profiles and social links to predict the missing attributes of target  ... 
doi:10.1109/access.2021.3064208 fatcat:rljfmzrkenfctjpcgpzrpvmume

Link Prediction in Relational Data

Benjamin Taskar, Ming Fai Wong, Pieter Abbeel, Daphne Koller
2003 Neural Information Processing Systems  
We apply the relational Markov network framework of Taskar et al. to define a joint probabilistic model over the entire link graph -entity attributes and links.  ...  We apply this method to two new relational datasets, one involving university webpages, and the other a social network.  ...  Abbeel was supported by a Siebel Grad. Fellowship.  ... 
dblp:conf/nips/TaskarWAK03 fatcat:uggrbco4pzbcbjzhx5eov4lvoa

Relational Deep Learning: A Deep Latent Variable Model for Link Prediction

Hao Wang, Xingjian Shi, Dit-Yan Yeung
2017 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Link prediction is a fundamental task in such areas as social network analysis, information retrieval, and bioinformatics.  ...  Usually link prediction methods use the link structures or node attributes as the sources of information.  ...  However, very few attempts have been made for the link prediction problem, especially for the joint modeling of node attributes and link structures on network data, which is crucial for link prediction  ... 
doi:10.1609/aaai.v31i1.10805 fatcat:lecb4auvkzg63ejoqjhyi523w4

Link Prediction with Contextualized Self-Supervision [article]

Daokun Zhang, Jie Yin, Philip S. Yu
2022 arXiv   pre-print
Link prediction aims to infer the existence of a link between two nodes in a network.  ...  The proposed CSSL is a generic and flexible framework in the sense that it can handle both transductive and inductive link prediction settings, and both attributed and non-attributed networks.  ...  ACKNOWLEDGMENTS This work is supported by a joint CRP research fund between the University of Sydney and Data61, CSIRO.  ... 
arXiv:2201.10069v1 fatcat:kehwqkrqfvgdpgiimxa3gk5ali

Network Model Selection for Task-Focused Attributed Network Inference [article]

Ivan Brugere and Chris Kanich and Tanya Y. Berger-Wolf
2017 arXiv   pre-print
Often these relationships are explicitly given, or we must learn a representation which generalizes and predicts observed behavior in underlying individual data (e.g. attributes or labels).  ...  We present a modular methodology using general, interpretable network models, task neighborhood functions found across domains, and several criteria for robust model selection.  ...  Our work uses two fundamental relational learning tasks, link prediction and collective classification to evaluate network models inferred from data.  ... 
arXiv:1708.06303v2 fatcat:vbadmkkyhbfn5h6eiooaimhvxi

Collective inference for network data with copula latent markov networks

Rongjing Xiang, Jennifer Neville
2013 Proceedings of the sixth ACM international conference on Web search and data mining - WSDM '13  
The popularity of online social networks and social media has increased the amount of linked data available in Web domains.  ...  In this work, we propose a novel latent relational model based on copulas which allows use to make predictions in a discrete label space while ensuring identical marginals and at the same time incorporating  ...  The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements either expressed or implied, of the NSF  ... 
doi:10.1145/2433396.2433477 dblp:conf/wsdm/XiangN13 fatcat:mi4avtthsrcsddcqjlcytj7itu

On Learning Mixed Community-specific Similarity Metrics for Cold-start Link Prediction

Linchuan Xu, Xiaokai Wei, Jiannong Cao, Philip S. Yu
2017 Proceedings of the 26th International Conference on World Wide Web Companion - WWW '17 Companion  
Existing metric learning methods for link prediction fail to consider communities which can be observed in many real-world social networks.  ...  Experiments on three real-world networks show that the intra-community homogeneities can be well preserved, and the mixed community-specific metrics perform better than a global similarity metric in terms  ...  Link Prediction We use stratified 90% links as training links, and the rest as test links. Also, the same number of negative links are randomly sampled for the evaluation purpose.  ... 
doi:10.1145/3041021.3054269 dblp:conf/www/XuWCY17a fatcat:7aee4y5c5zfmxb2yqe3kel2cki

Identifying graphs from noisy and incomplete data

Galileo Mark S. Namata, Lise Getoor
2010 SIGKDD Explorations  
Although the communication network is not directly appropriate for our task, we can use the information in the communication network to infer the social network that we would like to analyze.  ...  At the same time, there is a growing interest in analyzing these networks, in order to uncover general laws that govern their structure and evolution, and patterns and predictive models to develop better  ...  The second set of attributes is used for link prediction and consist of between 1 and 100 attributes (varied to control link existence ambiguity) generated using the method described in [14] .  ... 
doi:10.1145/1882471.1882477 fatcat:7un7fhkix5cwlaehrtqu2qnzb4

Latent co-interests' relationship prediction

Feng Tan, Li Li, Zheyu Zhang, Yunlong Guo
2013 Tsinghua Science and Technology  
Predictive problems, such as inferring friend relationship and co-author relationship between users have been explored.  ...  Experiments on two data sets (bookmarking and music network) demonstrate that this predictive method can achieve better results than the other three methods (ANN, NB, and SVM).  ...  Acknowledgements This work was supported by the National Natural Science Foundation of China (No. 61170192) and the Natural Science Foundations of Municipality of Chongqing (No. CSTC2012JJB40012).  ... 
doi:10.1109/tst.2013.6574676 fatcat:am7y7yniure5lptjgf3pgwmllu

Identifying graphs from noisy and incomplete data

Galileo Mark S. Namata, Lise Getoor
2009 Proceedings of the 1st ACM SIGKDD Workshop on Knowledge Discovery from Uncertain Data - U '09  
Although the communication network is not directly appropriate for our task, we can use the information in the communication network to infer the social network that we would like to analyze.  ...  At the same time, there is a growing interest in analyzing these networks, in order to uncover general laws that govern their structure and evolution, and patterns and predictive models to develop better  ...  The second set of attributes is used for link prediction and consist of between 1 and 100 attributes (varied to control link existence ambiguity) generated using the method described in [14] .  ... 
doi:10.1145/1610555.1610559 dblp:conf/kdd/NamataG09 fatcat:yvi2cdytgzf3befcowzlgs5ipy

A decoupled exponential random graph model for prediction of structure and attributes in temporal social networks

Vladimir Ouzienko, Yuhong Guo, Zoran Obradovic
2011 Statistical analysis and data mining  
In this article, we propose a new method to predict actor attributes and links in temporal networks.  ...  This is achieved by building two conditional predictors to jointly infer links and actor attributes.  ...  We thank Aleksandar Obradovic for very useful comments on a draft of this manuscript.  ... 
doi:10.1002/sam.10130 fatcat:oeoucalbbfclhi26y7nczbaveq

Gaze-aware graph convolutional network for social relation recognition

Xingming Yang, Fei Xu, Kewei Wu, Zhao Xie, Yongxuan Sun
2021 IEEE Access  
The SRG-GN introduce context objects in Social Relationship Graph Generation Network [5] , which use an explicit knowledge graph to represent human relation and attributes.  ...  We concatenate three features and use an FC layer with a unit of 1024 outputs to fuse them, and another FC layer to predict the social relation. E.  ... 
doi:10.1109/access.2021.3096553 fatcat:clriisccubf3vgvi7nfoa4tpoy
« Previous Showing results 1 — 15 out of 46,187 results