Scalable learning of collective behavior based on sparse social dimensions

By Lei Tang, Huan Liu. 2009

255 citations recorded by the source corpus.

Subfields: Statistical and Nonlinear Physics, Transportation, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistical and Nonlinear Physics

In Transportation

In Graph Learning

Citations in the corpus

DeepWalk: online learning of social representations (2014, methodology): “• YouTube [40] is a social network between users of the popular video sharing website.”
Deep Neural Networks for Learning Graph Representations (2016, methodology): “The learned vertex representations were shown to be effective across a few tasks, outperforming several previous approaches such as spectral clustering and modularity method (Tang and Liu 2009a; 2009b; 2011; Macskassy and Provost 2003).”
Scalable Learning of Collective Behavior (2012, unknown): “Ç”
Multi-relational matrix factorization using bayesian personalized ranking for social network data (2012, methodology): “Instead, we simply re-used the hyper-parameters from Tang and Liu for the SVM and from MR-BPR for the factorization.”
Leveraging social media networks for classification (2011, background): “Some preliminary results aiming at extracting sparse social dimensions have been presented in [ 40 ].”
A classification for community discovery methods in complex networks (2011, background): “There is interest especially in multidimensionality [75, 86, 101, 52, 54], perceived as a feature that is part of the solution and not only as an input to be preprocessed.”
Multi-label relational neighbor classification using social context features (2013, methodology): “In this paper, we select a subset of data (15000 nodes) from the original YouTube dataset 3 in [23] using snowball sampling , and re-1 tain 47 interest groups as our class label.”
Network Representation Learning: A Survey (2017, methodology): “Summary: The algorithms of learning latent social dimensions [31], [32], [33] only consider the community structure to learn vertex representation, while M-NMF [28] integrates microscopic structure (the second-order and highorder proximity) with the intra-community proximity.”
Structural Deep Network Embedding (2016, background): “• B LOGCATALOG [27], F LICKR [27] and Y OUTUBE [28]: They are social network of online users.”
A Survey on Network Embedding (2017, methodology): “The popularly used evaluation metrics for multi-label classiﬁcation problem include Micro-F1 and Macro-F1 (Tang and Liu 2009a).”
Homophily, Structure, and Content Augmented Network Representation Learning (2016, methodology): “Earlier work on NRL has attempted to partition a graph into different communities for creating social dimensions [8, 16, 17].”
PyTorch-BigGraph: A Large-scale Graph Embedding System (2019, methodology): “We evaluate PBG on the Freebase, LiveJournal and YouTube graphs and show that it matches the performance of existing embedding systems.”
Social Network Data Analytics (2011, methodology): “Often the Jaccard coef cient is used to compute document similarity in information retrieval [65].”
Discriminative Deep Random Walk for Network Classification (2016, methodology): “(Tang and Liu, 2009b) propose an edge-centric clustering scheme to extract sparse social dimensions for collective behavior prediction.”
State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems (2017, methodology): “…the deep architecture was demonstrated to outperform several multi-label network trafﬁc classiﬁcation methods such as SpectralClustering [201], Modularity [202], EdgeCluster [203], and the weighted-vote Relational Neighbor (wvRN) [204] for social networks like BlogCatalog, Flickr, and YouTube.”
Local Modeling of Attributed Graphs: Algorithms and Applications (2016, methodology): “16 2.4 Multi-label classification results in YOUTUBE . . . . . . . . . . . . . . . . . . . . 17 3.1 Multilabel classification results on BlogCatalog and DBLP.”
Accelerated Attributed Network Embedding (2017, background): “Tang and Liu [35] presented an edge-centric clustering scheme to facilitate the learning efficiency and alleviate the memory demand.”