Label Informed Attributed Network Embedding

By Xiao Huang, Jundong Li, Xia Hu. 2017

497 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Statistical and Nonlinear Physics

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

1. Xiangnan He
2. Tat-seng Chua
3. Xing Xie
4. Chengqi Zhang
5. Xia Hu
6. Xiang Wang
7. Zhiyuan Liu
8. Maosong Sun

In Information Systems

1. Xiangnan He
2. Tat-seng Chua
3. Xing Xie
4. Xiang Wang
5. Fuzheng Zhang
6. Hongwei Wang
7. Hanwang Zhang
8. Xia Hu

In Statistical and Nonlinear Physics

1. Chengqi Zhang
2. Peng Cui
3. Palash Goyal
4. Wenwu Zhu
5. Xingquan Zhu
6. Xiao Wang
7. Huan Liu
8. Xia Hu

Citations in the corpus

• SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction (2017, background): “, these methods can only address unsigned and homogeneous networks. Additionally, several studies focus on representation learning in the scenario of heterogeneous network [3, 32], attributed network [10], or signed network [29, 33]. However, these methods are specialized in only one particular type”
• Debiasing Community Detection: The Importance of Lowly Connected Nodes (2019, methodology): “In addition to CESNA, other methods have been proposed, such as Block-LDA [9], PAICAN [10], shared latent space models such as CLSM [7], and embedding-based approaches like LANE [11], which utilize node attributes in order to detect communities, or ELAINE [12], which utilizes”
• Graph Embedding Techniques, Applications, and Performance: A Survey (2017, background): “Other works ([46, 47, 48]) perform similar transformations between various node attributes and learn joint embedding.”
• Deep Anomaly Detection on Attributed Networks (2019, background): “Apart from traditional plain networks in which only node-to-node interactions are observed, attributed networks also encode a rich set of features for each node [2, 13, 18].”
• 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| .”
• Utilizing graph machine learning within drug discovery and development (2021, background): “sources, for instance, introducing a kernel defined on the feature matrix [80, 81].”
• Embedding Networks with Edge Attributes (2018, background): “Recently, some approaches have been proposed to incorporate node attributes in learning the representation [6, 12, 13].”
• 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., 2017] and heterogenous [Tang et al., 2015a; Chang et al., 2015; Huang and Mamoulis, 2017; Xu et al., 2017; Huang et al., 2017] network embeddings.”
• AliGraph: A Comprehensive Graph Neural Network Platform (2019, background): “LANE [25] smoothly incorporates label information into the attributed network embedding while preserving their correlations.”
• A Survey on Network Embedding (2017, methodology): “LANE (Huang, Li, and Hu 2017) is also proposed to incorporate the label information into the attributed network embedding.”
• Data Augmentation for Graph Neural Networks (2020, methodology): “We evaluate using 6 benchmark datasets across domains: citation networks (CORA, CITESEER (Kipf and Welling 2016a)), protein-protein interactions (PPI (Hamilton, Ying, and Leskovec 2017)), social networks (BLOGCATALOG, FLICKR (Huang, Li, and Hu 2017)), and air traffic (AIRUSA (Wu, He, and Xu 2019)).”
• Network Representation Learning: A Survey (2017, methodology): “, [8], [30], [45], [46], [47]), where representation learning and discriminative learning are simultaneously tack-”