Network Representation Learning with Rich Text Information

By Cheng Yang, Zhiyuan Liu, Deli Zhao, Maosong Sun, Edward Y. Chang. 2015

1,111 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, methodology): “factorization [56], and adding other regularizers to enforce TABLE 4 Graph Laplacian Eigenmaps Based Graph Embedding”
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec (2017, methodology): “Discussion on Yang et al. [46, 47] Two related works we want to discuss here are [46] and [47] by the same authors, where they claim they prove a closed form matrix factorized by DeepWalk. conclusion is then referred and used in a few following papers [29, 42, 48].”
Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking (2017, methodology): “Furthermore, for attributed graphs by leveraging both sources of information (network structure and attributes) one is able to learn more useful representations compared to approaches that only consider the graph (Yang et al., 2015; Pan et al., 2016; Ganguly & Pudi, 2017).”
Heterogeneous Information Network Embedding for Recommendation (2017, background): “Besides leaning network embedding from only the topology, there are alsomanyworks [51], [52], [53] leveraging node content information and other available graph information for the robust representations.”
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., 2016; Liang et al., 2018; Yang et al., 2015; Kipf & Welling, 2017).”
Paper2vec: Combining Graph and Text Information for Scientific Paper Representation (2017, methodology): “We set the dimension k in TADW at 160 as recommended by the authors in [13] for our CORA ML (small) dataset.”
Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba (2018, background): “ther embedded a complicate knowledge graph with the node in a hierarchical structure, like sub-categories, etc. Besides, textual information related to the nodes are incorporated into graph embedding [19, 24, 26, 27]. Moreover, in [5], Chang et al. propose a deep learning framework to simultaneously”
Deep Gaussian Embedding of Attributed Graphs: Unsupervised Inductive Learning via Ranking (2017, methodology): “Furthermore, as shown in [24, 29, 5], by leveraging both sources of information (the network structure and attributes) one is able to learn more useful representations compared to approaches that only consider the graph.”
Fast Network Embedding Enhancement via High Order Proximity Approximation (2017, methodology): “Besides the above NRL methods that focus on network topology, researchers also explore algorithms to incorporate meta information, e.g. text and label information, into NRL. TADW [Yang et al., 2015] takes text information into consideration under matrix factorization framework and MMDW [Tu et al., 2”
Adaptive Graph Encoder for Attributed Graph Embedding (2020, methodology): “methods, evaluation metrics, and parameter settings. 4.1 Datasets We conduct node clustering and link prediction experiments on four widely used network datasets (Cora, Citeseer, Pubmed [26] and Wiki [36]). Features in Cora and Citeseer are binary word vectors, while in Wiki and Pubmed, nodes are as”
Network Representation Learning: A Survey (2017, methodology): “The first, used by TADW [7] and HSCA [20], is to cou-”
Graph Neural Networks: A Review of Methods and Applications (2018, result): “Similar approaches such as node2vec [13], LINE [14] and TADW [15] also achieved breakthroughs.”
Attributed Social Network Embedding (2017, methodology): “shown that neural network models such as [30], [31] can”
Representation Learning for Attributed Multiplex Heterogeneous Network (2019, unknown): “Attributed Homogeneous Network (AHON) TADW [41]”
Unsupervised Attributed Multiplex Network Embedding (2019, background): “Such networks are called attributed networks, and have been extensively studied (Li et al. 2017; Hamilton, Ying, and Leskovec 2017; Yang et al. 2015; Zhang et al. 2018b; Gao and Huang 2018; Zhou et al. 2018; Veličković et al. 2019; Meng et al. 2019).”
Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment (2018, methodology): “This may be due to the fact that WANE-ww extracts information from the vertices and text sequences jointly, thus the obtained vertex embeddings are less noisy and perform more consistently with relatively small training ratios (Yang et al., 2015).”