Leveraging Label-Independent Features for Classification in Sparsely Labeled Networks: An Empirical Study
By Brian Gallagher, Tina Eliassi-Rad. 2008
73 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Representation & Self-Supervised 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
- Bryan Perozzi
- Jure Leskovec
- Jun Zhu
- William L. Hamilton
- Danai Koutra
- Hanghang Tong
- Stephan Günnemann
- Leman Akoglu
In Statistical and Nonlinear Physics
- Bryan Perozzi
- Jure Leskovec
- Hanghang Tong
- Danai Koutra
- Leman Akoglu
- Christos Faloutsos
- Jun Zhu
- Juzheng Li
In Representation & Self-Supervised Learning
- Bryan Perozzi
- Jure Leskovec
- William L. Hamilton
- Stephan Günnemann
- Jun Zhu
- Aditya Grover
- Aleksandar Bojchevski
- Steven S. Skiena
Citations in the corpus
- node2vec: Scalable Feature Learning for Networks (2016, background): “In networks, the conventional paradigm for generating features for nodes is based on feature extraction techniques which typically involve some seed hand-crafted features based on network properties [8, 11].”
- DeepWalk: online learning of social representations (2014, background): “We learn our latent social representations, instead of computing statistics related to centrality [13] or partitioning [41].”
- It's who you know: graph mining using recursive structural features (2011, background): “There has also been work on using local and global structural features to improve the performance of network classifiers[10].”
- A Fair Comparison of Graph Neural Networks for Graph Classification (2019, background): “The effect of adding structural features to general machine learning models for graphs has been investigated in Gallagher & Eliassi-Rad (2008); here, we focus on the impact of node degrees on performances for social datasets.”
- Discriminative Deep Random Walk for Network Classification (2016, background): “A variety of approaches have been proposed with the purpose of finding effective statistical information through the network (Gallagher and Eliassi-Rad, 2008; Henderson et al., 2011; Tang and Liu, 2011).”
- Local Modeling of Attributed Graphs: Algorithms and Applications (2016, background): “We learn our latent social representations, instead of computing statistics related to centrality [48] or partitioning [134].”
- RolX: structural role extraction & mining in large graphs (2012, background): “There has also been work on using local and global structural features to improve the performance of network classifiers [12].”