Structural Deep Network Embedding

By Daixin Wang, Peng Cui, Wenwu Zhu. 2016

2,811 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Statistical and Nonlinear Physics

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].”
Predicting multicellular function through multi-layer tissue networks (2017, neutral): “Finally, there exists recent work for task-dependent feature learning based on graph-speciﬁc deep network architectures (Zhai and Zhang, 2015; Li et al. , 2015; Xiaoyi et al. , 2014; Wang et al. , 2016a).”
SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction (2017, background): “useri. However, it is impractical to take xi directly as the sentiment representation of user i, as the adjacency vectoristoolongandsparseforfurtherprocessing.Recently,alotof network embedding models [8, 17, 23, 26] are proposed, which aim to learn low-dimension representations of vertices while pre”
Compositional Fairness Constraints for Graph Embeddings (2019, methodology): “, 2014), deep autoencoders (Wang et al., 2016), and graph neural networks (Hamilton et al.”
Auto-GNN: Neural architecture search of graph neural networks (2019, methodology): “Graph neural networks (GNN) [1, 2] has been demonstrated that it could achieve superior performance in modeling graph-structured data, within various domains such as social media [3–6] and bioinformatics [7, 8].”
Unsupervised Inductive Whole-Graph Embedding by Preserving Graph Proximity (2019, methodology): “In SDNE (Wang et al., 2016), an auto-encoder framework, the loss function is phrased as the reconstruction loss, the typical name in auto-encoders.”
Deep Graph Infomax (2018, background): “…best of our knowledge, the sole prior works that instead focuses on contrasting “global” and “local” representations on graphs do so via (auto-)encoding objectives on the adjacency matrix (Wang et al., 2016) and incorporation of community-level constraints into node embeddings (Wang et al., 2017).”
Representation Learning on Graphs: Methods and Applications (2017, methodology): “Deep Neural Graph Representations (DNGR) [10] and Structural Deep Network Embeddings (SDNE) [58] address the ﬁrst problem outlined above: unlike the direct encoding methods, they directly incorporate graph structure into the encoder algorithm.”
FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling (2018, background): “Meanwhile, there appear a few deep neural network architectures, which better capture the nonlinearity within graphs, such as SDNE (Wang et al., 2016).”
A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, methodology): “Graph visualization generates visualizations of a graph on a low dimensional space [20], [23], [48], [55], [58], [73].”
Adversarially Regularized Graph Autoencoder (2018, background): “SDNE [Wang et al. , 2016] and DNGR [Cao et al. , 2016] employ deep autoencoders to preserve the graph proximities and model positive pointwise mutual information (PPMI).”
A Comprehensive Survey on Graph Neural Networks (2019, methodology): “Concurrently, Structural Deep Network Embedding (SDNE) [60] uses a stacked autoencoder to preserve the node ﬁrst-order proximity and second-order proximity jointly.”
Graph Embedding Techniques, Applications, and Performance: A Survey (2017, methodology): “[23] proposed to use deep autoencoders to preserve the first and second order network proximities.”
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.”
struc2vec: Learning Node Representations from Structural Identity (2017, background): “Similarly to subgraph2vec, considerable eort has recently been made on learning richer representations for network nodes [4, 24].”
Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking (2017, methodology): “Note that SDNE (Wang et al., 2016) and GraphSAGE (Hamilton et al., 2017) cannot be applied in this scenario, since they also require the edges for the unseen nodes to produce an embedding.”
AliGraph: A Comprehensive Graph Neural Network Platform (2019, methodology): “Node2Vec [18] adds two parameters to control the random walk process while SDNE [50] proposes a structure-preserving embedding method.”
Network Representation Learning: A Survey (2017, methodology): “However, as stated in [19], [20], the structure-level similarity between vertices is reflected not only at the local neighborhood struc-”