Role-Oriented Graph Auto-encoder Guided by Structural Information

Guo, Xuan; Zhang, Wang; Wang, Wenjun; Yu, Yang; Wang, Yinghui; Jiao, Pengfei

doi:10.1007/978-3-030-59416-9_28

Cited by 15 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, DRNE [125] develops a deep learning method with a normalized long short-term memory (LSTM) layer to learn regular equivalence by recursively aggregating neighbors' representations for each node. GAS [141] utilizes graph neural networks (GNN) to capture node structure by applying sum-pooling propagation instead of the graph convolutional networks (GCN) [142] to better capture local node structures. For training, GAS extracts features similarly to ReFeX and aggregates them only once.…”

Section: Role Discovery Modelsmentioning

confidence: 99%

Role-Aware Information Spread in Online Social Networks

Bartal

Jagodnik

2021

Entropy

View full text Add to dashboard Cite

Understanding the complex process of information spread in online social networks (OSNs) enables the efficient maximization/minimization of the spread of useful/harmful information. Users assume various roles based on their behaviors while engaging with information in these OSNs. Recent reviews on information spread in OSNs have focused on algorithms and challenges for modeling the local node-to-node cascading paths of viral information. However, they neglected to analyze non-viral information with low reach size that can also spread globally beyond OSN edges (links) via non-neighbors through, for example, pushed information via content recommendation algorithms. Previous reviews have also not fully considered user roles in the spread of information. To address these gaps, we: (i) provide a comprehensive survey of the latest studies on role-aware information spread in OSNs, also addressing the different temporal spreading patterns of viral and non-viral information; (ii) survey modeling approaches that consider structural, non-structural, and hybrid features, and provide a taxonomy of these approaches; (iii) review software platforms for the analysis and visualization of role-aware information spread in OSNs; and (iv) describe how information spread models enable useful applications in OSNs such as detecting influential users. We conclude by highlighting future research directions for studying information spread in OSNs, accounting for dynamic user roles.

show abstract

Section: Role Discovery Modelsmentioning

confidence: 99%

Role-Aware Information Spread in Online Social Networks

Bartal

Jagodnik

2021

Entropy

View full text Add to dashboard Cite

show abstract

“…GAS [68]. Graph Neural Networks have the power to capture structure as they are closely related to Weisfeiler-Lehman (WL) test in some ways [81].…”

Section: Structural Information Reconstruction/guidance Drnementioning

confidence: 99%

“…struc2vec [39], struc2gauss [64], Role2Vec [65] and NODE2BITS [67] are all based on random walk. DRNE [50], GraLSP [70], GAS [68] and RESD [69] pertain to the scope of deep learning. In the subsequent experiments, all the parameters are fine-tuned.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…Generally speaking, the methods based on deep learning are relatively efficient compared to others, especially for the methods that need higher-order features. GAS [68], RESD [69] and NODE2BITS [67] are the three most efficient methods and RolX [38] also has competitive results. struc2gauss [64], SEGK [56] and Role2vec [65] cost more time to learn the node embeddings since they need to compute higher-order features, e.g., motif.…”

Section: Efficiency Analysismentioning

confidence: 99%

“…It is also a common way for understanding the network structure and the methods. In this section, we show the t-SNE results of these methods based on the Brazil network in Fig 7 . It can be observed that, RIDεRs [58], GraphWave [59], SEGK [56], struc2vec [39], struc2gauss [64], DRNE [50], GAS [68] and RESD [69] can be more accurate to identify the labels compared with others. The cyan nodes correspond to the airports with large passenger flow and all these methods can embed it effectively except NODE2BITS [67].…”

Section: Visualization Analysismentioning

confidence: 99%

See 2 more Smart Citations

A Survey on Role-Oriented Network Embedding

Jiao¹,

Guo²,

Pan³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, Network Embedding (NE) has become one of the most attractive research topics in machine learning and data mining. NE approaches have achieved promising performance in various of graph mining tasks including link prediction and node clustering and classification. A wide variety of NE methods focus on the proximity of networks. They learn community-oriented embedding for each node, where the corresponding representations are similar if two nodes are closer to each other in the network. Meanwhile, there is another type of structural similarity, i.e., role-based similarity, which is usually complementary and completely different from the proximity. In order to preserve the role-based structural similarity, the problem of role-oriented NE is raised. However, compared to community-oriented NE problem, there are only a few role-oriented embedding approaches proposed recently. Although less explored, considering the importance of roles in analyzing networks and many applications that role-oriented NE can shed light on, it is necessary and timely to provide a comprehensive overview of existing role-oriented NE methods. In this review, we first clarify the differences between community-oriented and role-oriented network embedding. Afterwards, we propose a general framework for understanding role-oriented NE and a two-level categorization to better classify existing methods. Then, we select some representative methods according to the proposed categorization and briefly introduce them by discussing their motivation, development and differences. Moreover, we conduct comprehensive experiments to empirically evaluate these methods on a variety of role-related tasks including node classification and clustering (role discovery), top-k similarity search and visualization using some widely used synthetic and real-world datasets. Finally, we further discuss the research trend of role-oriented NE from the perspective of applications and point out some potential future directions. The source code and datasets used in the experiments are available at Github.

show abstract