Node Classification in Social Networks

By Smriti Bhagat, Graham Cormode, S. Muthu Muthukrishnan. 2011

550 citations recorded by the source corpus.

When dealing with large graphs, such as those that arise in the context of online social networks, a subset of nodes may be labeled. These labels can indicate demographic values, interest, beliefs or other characteristics of the nodes (users). A core problem is to use this information to extend the labeling so that all nodes are assigned a label (or labels).

Subfields: Artificial Intelligence, Information Systems, Statistical and Nonlinear Physics, 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 Artificial Intelligence

In Information Systems

In Statistical and Nonlinear Physics

In Graph Learning

Citations in the corpus

LINE: Large-scale Information Network Embedding (2015, methodology): “Such a low-dimensional embedding is very useful in a variety of applications such as visualization [21], node classification [3], link prediction [10], and recommendation [23].”
Representation Learning on Graphs: Methods and Applications (2017, background): “, degrees or clustering coefficients) [6], kernel functions [57], or carefully engineered features to measure local neighborhood structures [39].”
PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks (2015, background): “, node classification [3] and link prediction [13].”
Graph Embedding Techniques, Applications, and Performance: A Survey (2017, methodology): “Graph analytic tasks can be broadly abstracted into the following four categories: (a) node classification [6], (b) link prediction [5], (c) clustering [7], and (d) visualization [8].”
Graph Transformer Networks (2019, methodology): “Conventionally, hand-crafted features have been used such as simple graph statistics [2], graph kernel [34], and engineered features from a local neighbor structure [23].”
DropEdge: Towards Deep Graph Convolutional Networks on Node Classification (2019, background): “Graph Convolutional Networks (GCNs), which exploit message passing or equivalently certain neighborhood aggregation function to extract high-level features from a node as well as its neighborhoods, have boosted the state-of-the-arts for a variety of tasks on graphs, such as node classification (Bhag”
Network Representation Learning: A Survey (2017, background): “The problem of vertex classification aims to predict the labels of unlabeled vertices given a partially labeled network [10], [11].”
Deep learning for noise-tolerant RDFS reasoning (2019, unknown): “Graph analytics tasks include centrality analysis, nodes classification [41], link prediction [42] etc.”
Large-Scale Embedding Learning in Heterogeneous Event Data (2016, background): “The lowdimensional vectors, as distributed representations of objects, are beneficial for various downstream applications, such as exploratory data analysis, link prediction [1], object clustering [2], classification [3], and recommendation [4].”
Community Preserving Network Embedding (2017, background): “Benefited from this, a variety of applications on networks, such as node classification (Bhagat, Cormode, and Muthukrishnan 2011) and recommendation (Yu et al. 2014), can be directly conducted by the off-the-shelf machine learning methods in the low-dimensional vector space.”
LRBM: A Restricted Boltzmann Machine Based Approach for Representation Learning on Linked Data (2014, methodology): “SSC and ICA have worse performance on SocialE while achieve relatively better performance on Robot.”
A Survey of Signed Network Mining in Social Media (2015, methodology): “…which aims to learn low-dimensional vector representations for nodes, has been proven to be useful in many tasks of social network analysis such as link prediction[Liben-Nowell and Kleinberg 2007], community detection[Papadopoulos et al. 2012], and node classification[Bhagat et al. 2011].”
Deep Representation Learning for Social Network Analysis (2019, methodology): “…information in networks, most previous efforts mainly rely on handcrafted features, such as kernel functions (Vishwanathan et al., 2010), graph statistics (i.e., degrees or clustering coefficients) (Bhagat et al., 2011), or other carefully engineered features (Liben-Nowell and Kleinberg, 2007).”
Exploiting Edge Features in Graph Neural Networks. (2018, background): “degrees) [5], kernel functions [28][24] or other hand-crafted features which measure local neighborhood structures.”