Discriminative Deep Random Walk for Network Classification

By Juzheng Li, Jun Zhu. 2016

125 citations recorded by the source corpus.

Deep Random Walk (DeepWalk) can learn a latent space representation for describing the topological structure of a network. However, for relational network classification, DeepWalk can be suboptimal as it lacks a mechanism to optimize the objective of the target task. In this paper, we present Discriminative Deep Random Walk (DDRW), a novel method for relational network classification. By solving a joint optimization problem, DDRW can learn the latent space representations that well capture the topological structure and meanwhile are discriminative for the network classification task. Our experimental results on several real social networks demonstrate that DDRW significantly outperforms DeepWalk on multilabel network classification tasks, while retaining the topological structure in the latent space. DDRW is stable and consistently outperforms the baseline methods by various percentages of labeled data. DDRW is also an online method that is scalable and can be naturally parallelized.

Subfields: Artificial Intelligence, 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. Shirui Pan
2. Zhiyuan Liu
3. Guodong Long
4. Maosong Sun
5. Jing Jiang
6. Chengqi Zhang
7. Ruiqi Hu
8. Cheng Yang

In Statistical and Nonlinear Physics

1. Shirui Pan
2. Chengqi Zhang
3. Guodong Long
4. Ruiqi Hu
5. Jing Jiang
6. Cheng Yang
7. Zhiyuan Liu
8. Binqiang Zhao

Citations in the corpus

• Graph embedding on biomedical networks: methods, applications and evaluations (2019, unknown): “For example, DDRW (Li et al., 2016) and MMDW (Tu et al.”
• Fast Network Embedding Enhancement via High Order Proximity Approximation (2017, methodology): “GCN [Kipf and Welling, 2017], DDRW [Li et al., 2016] and Planetoid [Yang et al., 2016] are also proposed for semi-supervised graph embeddings.”
• 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”
• Learning Graph Embedding With Adversarial Training Methods (2019, background): “Other random walk variants include hierarchical representation learning approach (HARP) [29], and discriminative deep random walk (DDRW) [30], and Walklets [31].”
• SNE: Signed Network Embedding (2017, methodology): “Network embedding Several network embedding methods including DeepWalk [26], LINE [30], Node2vec [9], Deep Graph Kernels [36] and DDRW [17] have been proposed.”