Max-Margin DeepWalk: Discriminative Learning of Network Representation

By Cunchao Tu, Weicheng Zhang, Weicheng Zhang, Zhiyuan Liu, Maosong Sun. 2016

263 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.

1. Shirui Pan
2. Xiao Wang
3. Daokun Zhang
4. Chuan Shi
5. Vincent Wenchen Zheng
6. Peng Cui
7. Feng Xia
8. Hongyun Cai

Citations in the corpus

• A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “Graph visualization generates visualizations of a graph on a low dimensional space [20], [23], [48], [55], [58], [73].”
• 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].”
• A Survey on Network Embedding (2017, background): “Citeseer is used in (Yang et al. 2015; Pan et al. 2016; Tu et al. 2016).”
• SNE: Signed Network Embedding (2017, background): “In [32, 39] the authors consider the node label information and present semi-supervised models to learn the network embedding.”
• Fast Network Embedding Enhancement via High Order Proximity Approximation (2017, background): “, 2015] takes text information into consideration under matrix factorization framework and MMDW [Tu et al., 2016] learns semi-supervised network embeddings with maxmargin constraints between vertices from different labels.”
• Network Representation Learning: A Survey (2017, methodology): “, DDRW [45], MMDW [46], TLINE [47], DMF [8], SemiNE [49]) is to enforce classifica-”
• Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment (2018, background): “This results in models that are not able to fully capture the relationships between vertices of the network (Per-ozzi et al., 2014; Tu et al., 2016).”
• Graph embedding on biomedical networks: methods, applications and evaluations (2019, unknown): “, 2016) and MMDW (Tu et al., 2016) jointly optimize the objective of DeepWalk with a Support Vector Machine (SVM) classification loss to incorporate label information.”
• Heterogeneous Information Network Embedding for Recommendation (2017, methodology): “On the other hand, network embedding has shown its potential in structure feature extraction and has been successfully applied in many data mining tasks [39], [40], [41], [42], such as classification [43], clustering [44], [45] and recommendation [46], [47].”
• Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba (2018, methodology): “mption that node with similar side information should be closer in the embedding space. To achieve this, a joint framework is proposed to optimize the embeddingobjectivefunctionwithaclassifierfunction[11,20].And in [25] Xie et al. further embedded a complicate knowledge graph with the node in a hier”
• Graph Learning: A Survey (2021, methodology): “The MMDW [94] is another model based on DeepWalk, which is a kind of semi-supervised network embedding algorithm, by leveraging labelling information of vertices to enhance the performance.”
• Community Preserving Network Embedding (2017, methodology): “Further, the labeling information is considered by combining the matrix factorization and the max-margin classifier (Tu et al. 2016).”