Heterogeneous Network Embedding via Deep Architectures

By Shiyu Chang, Wei Han, Jiliang Tang, Guo-Jun Qi, Charu C. Aggarwal, Thomas S. Huang. 2015

597 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Statistical and Nonlinear Physics

In Graph Learning

Citations in the corpus

SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction (2017, background): “ell as their heterogeneous embedding ei and ej, the predicted sentiment s¯ij can be calculated as s¯ij = f (i,j), where f (·,·)is specific similarity measurement function. For example: •Inner product [3, 5], i.e., s¯ij = eT i j + b, where is a trainable bias parameter; •Euclidean distance [26], i.e.”
Representation Learning on Graphs: Methods and Applications (2017, background): “A general strategy for dealing with this issue is to (i) use different encoders for nodes of different types [12] and (ii) extend pairwise decoders with type-speciﬁc parameters [42, 52].”
A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, methodology): “ChebNet graph GCN [72] Graph Convolutional Network graph GNN [120] Graph Neural Network graph [121] adapted Graph Neural Network molecules graph GGS-NNs [122] adapted Graph Neural Network graph HNE [33] CNN + FC graph with image and text DUIF [35] a hierarchical deep model social curation network Pr”
Differential Recurrent Neural Networks for Action Recognition (2015, neutral): “Compared with many existing spatio-temporal features [17, 29, 5, 24] from the time-series data, RNNs use either a hidden layer [28] or a memory cell [14] to learn the timeevolving states which models the underlying dynamics of the input sequence.”
Graph Embedding Techniques, Applications, and Performance: A Survey (2017, background): “Heterogeneous Network Embedding (HNE) [45] learns representation for each modality of the network and then unifies them into a common space using linear transformations.”
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec (2017, background): “…[36], Deep-Walk [28], LINE [35], a growing 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,…”
Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking (2017, background): “Heterogeneous networks are consider in (Tang et al., 2015a; Chang et al., 2015), while Huang et al. similarly to Pan et al. (2016) considers labels.”
Attributed Network Embedding for Learning in a Dynamic Environment (2017, methodology): “[7] used deep learning techniques to learn a joint feature representation for heterogeneous networks.”
ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation (2017, background): “…heterogeneous data representation can be learnt by minimizing the distances in the projected latent spaces (Bordes et al. 2013; Lin et al. 2015; Chang et al. 2015), there are no explicit supervisions like mapping or inferencing between any pair of user behaviors that could help build the…”
Deep Learning on Graphs: A Survey (2018, unknown): “For example, most methods focus on homogeneous graphs, while heterogeneous graphs are seldom studied, especially those containing different modalities such as those in [157].”
Under review as a conference paper at ICLR 2019 MILE : A Multi-Level Framework for Scalable Graph Embedding (2018, unknown): “This also led to the proliferation of network embedding methods for information-rich graphs, including heterogeneous information networks (Chang et al., 2015; Dong et al., 2017) and attributed graphs (Pan et al.”
Deep Gaussian Embedding of Attributed Graphs: Unsupervised Inductive Learning via Ranking (2017, background): “Heterogeneous networks are consider in [25, 2], while [11] simiarly to [20] considers labels.”
A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources (2020, unknown): “HNE [70] is proposed to learn embeddings for the cross-model data in HG, but it ignores the various types of links.”
Representation Learning for Attributed Multiplex Heterogeneous Network (2019, background): “The goal is to find a function f r : V → R d for every edge type r , where d ≪ |V| .”
SNE: Signed Network Embedding (2017, background): “The heterogeneous network embedding models are studied in [4, 25, 29, 37].”