LATTE: Application Oriented Social Network Embedding

  title={LATTE: Application Oriented Social Network Embedding},
  author={Lin Meng and Jiyang Bai and Jiawei Zhang},
  journal={2019 IEEE International Conference on Big Data (Big Data)},
In recent years, many research works propose to embed the network structured data into a low-dimensional feature space, where each node will be represented as a feature vector. However, due to the detachment of the embedding process with external tasks, the learned embedding results by most existing embedding models can be ineffective for application tasks with specific objectives, e.g., community detection, network alignment or information diffusion. In this paper, we propose to study the… 

Figures and Tables from this paper

Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning

A novel self-supervised representation learning method via Sub-graph Contrast, namely Subg-Con, is proposed by utilizing the strong correlation between central nodes and their sampled subgraphs to capture regional structure information and has prominent performance advantages in weaker supervision requirements, model learning scalability, and parallelization.



LINE: Large-scale Information Network Embedding

A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures.

Least Cost Influence in Multiplex Social Networks: Model Representation and Analysis

This paper tackles the LCI problem in multiplex OSNs by reducing multiplex networks to a single network via various coupling schemes while preserving the most influence propagation properties.

Task-Guided and Path-Augmented Heterogeneous Network Embedding for Author Identification

This model can obtain significantly better accuracy at identifying the true authors comparing to existing methods and is extended to incorporate meta paths in heterogeneous networks, and select paths according to the specific task.

Meta-path based multi-network collective link prediction

An effective general link formation prediction framework, Mli (Multi-network Link Identifier), is proposed in this paper to solve the multi-network link (formation) prediction problem.

BL-MNE: Emerging Heterogeneous Social Network Embedding Through Broad Learning with Aligned Autoencoder

A new embedding framework, namely "Deep alIgned autoencoder based eMbEdding" (DIME), is introduced, which handles the diverse link and attribute in a unified analytic based on broad learning, and introduces the multiple aligned attributed heterogeneous social network concept to model the network structure.

Mining topic-level influence in heterogeneous networks

A generative graphical model is proposed which utilizes the heterogeneous link information and the textual content associated with each node in the network to mine topic-level direct influence and a topic- level influence propagation and aggregation algorithm is proposed to derive the indirect influence between nodes.

Modeling Topic Diffusion in Multi-Relational Bibliographic Information Networks

Two variations of the linear threshold model for multi-relational networks are proposed, by considering the aggregation of information at either the model level or the relation level, and can determine the diffusion power of each relation type, which helps to understand the diffusion process better in the multi- Relational bibliographic network scenario.

Inferring anchor links across multiple heterogeneous social networks

This paper proposes to extract heterogeneous features from multiple heterogeneous networks for anchor link prediction, including user's social, spatial, temporal and text information, and derives an effective solution, MNA (Multi-Network Anchoring), to infer anchor links w.r.t. the one-to-one constraint.

Maximizing the spread of influence through a social network

An analysis framework based on submodular functions shows that a natural greedy strategy obtains a solution that is provably within 63% of optimal for several classes of models, and suggests a general approach for reasoning about the performance guarantees of algorithms for these types of influence problems in social networks.

Community Detection for Emerging Networks

A new general closeness measure, intimacy, is introduced in this paper, based on both link and attribution information across multiple networks, and an effective and efficient method, CAD, is proposed to propagate information from developed network to calculate effective intimacy scores among users in emerging networks.