GraRep: Learning Graph Representations with Global Structural Information

By Shaosheng Cao, Wei Dang Lu, Qiongkai Xu. 2015

1,738 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, 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 Representation & Self-Supervised Learning

In Graph Learning

Citations in the corpus

Inductive Representation Learning on Large Graphs (2017, neutral): “Low-dimensional vector embeddings of nodes in large graphs1 have proved extremely useful as feature inputs for a wide variety of prediction and graph analysis tasks [5, 11, 28, 35, 36].”
Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, methodology): “Finally, in the network analysis community, several works constructed graph embeddings [28, 38, 12, 17, 44] methods inspired by the Word2Vec technique [27].”
Attacking Graph-based Classification via Manipulating the Graph Structure (2019, methodology): “Some graph neural network methods [11,28,48,58] ﬁrst learn feature vectors for nodes in an unsupervised learning fashion (also known as graph embedding ); then they use the feature vectors and the training dataset to learn a standard binary classiﬁer (e.g., logistic regression); and ﬁnally they use…”
Representation Learning on Graphs: Methods and Applications (2017, methodology): “The Graph Factorization (GF) algorithm 4 [1], GraRep [9], and HOPE [44] all fall ﬁrmly within this class.”
FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling (2018, methodology): “A major category consists of factorization based algorithms that yield the embedding through matrix factorizations; see, e.g., Roweis & Saul (2000); Belkin & Niyogi (2001); Ahmed et al. (2013); Cao et al. (2015); Ou et al. (2016).”
Geometric Deep Learning: Going beyond Euclidean data (2016, methodology): “mbedding (LLE) [35], stochastic neighbor embedding (t-SNE) [36], spectral embeddings such as Laplacian eigenmaps [37] and diffusion maps [38], and deep models [39]. Most recent approaches [40], [41], [42] tried to apply the successful word embedding model [43] to graphs. Instead of embedding the poi”
A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, methodology): “ity matrix that describes local pairwise distances HOPE [106] Katz Index W= (I A) 1A; Personalized Pagerank W= (1 )(I P) 1 Eq. 5 Common neighbors W= A2; Adamic-Adar W= A(1= P j (A ij+ A ji))A GraRep [21] Wk ij = log( A^k ij P t A^k ij ) log( jV ), where A^ = D 1S, D ij= ˆ P p A ip;i= j 0;i6= j Eq. ”
Adversarially Regularized Graph Autoencoder (2018, methodology): “As a graph can be mathematically represented as an adjacency matrix, many matrix factorization approaches such as GraRep [Cao et al., 2015], HOPE [Ou et al.”
Self-Supervised Learning: Generative or Contrastive (2020, methodology): “In general, existing network embedding approaches are broadly categorized as (1) factorization-based approaches such as NetMF [110], [111], GraRep [18], HOPE [102], (2) shallow embedding approaches such as DeepWalk [106], LINE [134], HARP [21], and (3) neural network approaches [19], [86].”
Deep Neural Networks for Learning Graph Representations (2016, methodology): “Our recent approach called GraRep (Cao, Lu, and Xu 2015) has been shown to achieve good empirical results on the task of learning graph representations .”
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec (2017, background): “…[7, 11, 17, 34], direct network embedding [27], semi-supervised network embedding [18, 42, 49], network embedding with rich vertex attributes [41, 47], network embedding with high order structure [5, 15], network embedding via deep neural network [6, 22, 44], signed network embedding [9], etc.”
Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking (2017, methodology): “GraRep (Cao et al., 2015) is a factorization based method that considers local and global structural information.”
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs (2019, background): “…the latter data types, there exist renewed interests in the learning of graph representations (Perozzi, Al-Rfou, and Skiena 2014; Tang et al. 2015; Cao, Lu, and Xu 2015; Ou et al. 2016; Grover and Leskovec 2016) on both the node and the graph level, now parameterized by deep neural networks…”
Learning Social Image Embedding with Deep Multimodal Attention Networks (2017, methodology): “Most of the network embedding methods adopt the shallow model, e.g., DeepWalk [20], and GraRep [2], etc. DeepWalk [20] learns the latent representations of the nodes of a social network from truncated random walks in the network.”
On the Equivalence between Positional Node Embeddings and Structural Graph Representations (2019, methodology): “les obtained using MC-SVD on the disconnected food web graph shown in Figure 1. particular method. This literature features a myriad of methods, e.g., matrix factorization (Belkin & Niyogi, 2002; Cao et al., 2015; Ahmed et al., 2013; Ou et al., 2016), implicit matrix factorization (Mikolov et al”
Adversarial Network Embedding (2017, methodology): “• GraRep (Cao, Lu, and Xu 2015): GraRep preserves node proximities by constructing different k -step probability transition matrices.”