Asymmetric Transitivity Preserving Graph Embedding

By Mingdong Ou, Peng Cui, Jian Pei, Ziwei Zhang, Wenwu Zhu. 2016

1,319 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Statistical and Nonlinear Physics, 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 Cognitive Neuroscience

In Statistical and Nonlinear Physics

In Representation & Self-Supervised Learning

In Graph Learning

Citations in the corpus

SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction (2017, background): “cted,which implies that for two nodes i and j in the network, edges (i,j)and (j,i)may coexist and their values are not necessarily identical. A few recent studies have focused on this asymmetry issue [16, 36]. In this work, whether the basic SHINE model can characterize asymmetry depends on the choi”
Representation Learning on Graphs: Methods and Applications (2017, methodology): “(z i;z j) s G(v i;v j) Matrix Graph Factorization [1] z> i z j A i;j kDEC(z i;z j) s G(v i;v j)k22 factorization GraRep [9] z> i z j A i;j;A 2 i;j;:::;A k i;j kDEC(z i;z j) s G(v i;v j)k22 HOPE [45] z> i z j general kDEC(z i;z j) s G(v i;v j)k22 Random walk DeepWalk [47] e z> i zj P k2V ”
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).”
A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “nodes of interest to a given node based on certain criteria such as similarity [3], [16], [43], [45], [47], [106].”
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].”
Graph Embedding Techniques, Applications, and Performance: A Survey (2017, methodology): “HOPE [24] preserves higher order proximity by minimizing ‖S−YsY T t ‖(2)F , where S is the similarity matrix.”
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec (2017, background): “…number of literature has paid the attention to this area, for example, heterogeneous network embedding [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…”
A Semi-Supervised Graph Attentive Network for Financial Fraud Detection (2019, methodology): “Some further works [20], [21] use the matrix factorization to factorize high-order relation matrix.”
Exploiting Edge Features in Graph Neural Networks. (2018, methodology): “One kind of embedding approaches are based on matrix-factorization, e.g. Laplacian Eigenmap (LE) [4], Graph Factorization (GF) algorithm [2], GraRep [7], and HOPE [21].”
Fast Network Embedding Enhancement via High Order Proximity Approximation (2017, background): “Other extensions include asymmetric transitivity [Ou et al., 2016], community preserving [Wang et al.”
Graph Representation Learning (2020, methodology): “Some examples of this style of node embedding algorithms include the Graph Factorization (GF) approach1 [Ahmed et al., 2013], GraRep [Cao et al., 2015], and HOPE [Ou et al., 2016].”
Finding and Characterizing Information Warfare Campaigns (2020, methodology): “Embedding (HOPE) algorithm [187] and Facebook Biggraph [153], with Singular Value Decomposition of the Adjacency Matrix used as a baseline.”
SNE: Signed Network Embedding (2017, background): “HOPE [24] focuses on preserving the asymmetric transitivity of a directed network by approximating highorder proximity of a network.”
dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning (2018, methodology): “It has been shown that such techniques can outperform traditional link prediction methods on graphs [8, 9].”
A Survey on Deep Semi-Supervised Learning (2021, methodology): “The random surfing design is used to create a stochastic matrix equivalent to the similarity measure matrix in HOPE [74] on the input graph.”
DynGEM: Deep Embedding Method for Dynamic Graphs (2018, background): “…demonstrated that graph embedding is superior to alternatives in many supervised learning tasks, such as node classiﬁcation, link prediction and graph reconstruction [Ahmed et al. , 2013; Perozzi et al. , 2014; Cao et al. , 2015; Tang et al. , 2015; Grover and Leskovec, 2016; Ou et al. , 2016].”
Learning Graph Embedding With Adversarial Training Methods (2019, methodology): “GraRep [18] integrates the global topological information of the graph into the learning process to represent each node into a low-dimensional space; HOPE [19] preserves the asymmetric transitivity by approximating high-order proximity for a better performance on capturing topological information of”
Topological Recurrent Neural Network for Diffusion Prediction (2017, background): “GraRep [32] and HOPE [33] preserve high-order proximity by learning node embedding from a high-order adjacency matrix.”
A Novel Neural Source Code Representation Based on Abstract Syntax Tree (2019, methodology): “In order to overcome the limitations of the above AST-based neural networks, one solution is to introduce explicit (long-term) control ﬂow and data dependencies graphs and employ a Graph Embedding technique [24] to represent source code.”