Deep Network Embedding for Graph Representation Learning in Signed Networks

@article{Shen2020DeepNE,
  title={Deep Network Embedding for Graph Representation Learning in Signed Networks},
  author={X. Shen and Fu-lai Chung},
  journal={IEEE Transactions on Cybernetics},
  year={2020},
  volume={50},
  pages={1556-1568}
}
  • X. Shen, F. Chung
  • Published 7 January 2019
  • Computer Science
  • IEEE Transactions on Cybernetics
Network embedding has attracted an increasing attention over the past few years. As an effective approach to solve graph mining problems, network embedding aims to learn a low-dimensional feature vector representation for each node of a given network. The vast majority of existing network embedding algorithms, however, are only designed for unsigned networks, and the signed networks containing both positive and negative links, have pretty distinct properties from the unsigned counterpart. In… 

Figures and Tables from this paper

Network Together: Node Classification via Cross-Network Deep Network Embedding
TLDR
This article studies a cross-network node classification problem, which aims at leveraging the abundant labeled information from a source network to help classify the unlabeled nodes in a target network, and proposes a novel cross- Network embedding model that significantly outperforms the state-of-the-art network embedding algorithms in cross- network node classification.
Semisupervised Community Preserving Network Embedding with Pairwise Constraints
TLDR
Experimental results show that the node representations learned after incorporating the pairwise constraints can obtain higher accuracy in node clustering task and the results of link prediction, and network visualization tasks indicate that the semisupervised model SMNMF is more discriminative than unsupervised ones.
Semisupervised Community PreservingNetwork Embeddingwith Pairwise Constraints
TLDR
Experimental results show that the node representations learned after incorporating the pairwise constraints can obtain higher accuracy in node clustering task and the results of link prediction, and network visualization tasks indicate that the semisupervised model SMNMF is more discriminative than unsupervised ones.
Network Embedding for Cross-network Node Classification
TLDR
A cross-network deep network embedding (CDNE) model is proposed to embed the nodes from the source network and the target network into a unified low-dimensional latent space and significantly outperforms the state-of-the-art related algorithms for node classification in thetarget network.
Signed Network Embedding Based on Noise Contrastive Estimation and Deep Learning
TLDR
Considering the sparsity of signed networks, a signed network embedding algorithm NDSE is proposed based on noise contrastive estimation model and deep learning framework and optimizes a carefully designed objective function that preserves both local and global network structures.
Adversarial Deep Network Embedding for Cross-network Node Classification
TLDR
An adversarial cross-network deep network embedding (ACDNE) model is proposed to integrate adversarial domain adaptation with deep networkembedding so as to learn network-invariant node representations that can also well preserve the network structural information.
A Comparison of Methods for Link Sign Prediction with Signed Network Embeddings
TLDR
This paper bridges the literature gap providing a quantitative and qualitative benchmark of the four most prominent representation learning methods for signed networks, and showcases the superiority of the StEM method over its competitors both from a predictive performance and runtime perspective.
Inter-Intra Information Preserving Attributed Network Embedding
TLDR
A novel model named Inter-Intra Information Preserving Attributed Network Embedding (IINE) is proposed to effectively learn the node representations of attributed network, which can not only capture the inter-relation between structure and attribute information with less information distortion but also effectively preserve the intra-characteristic of each information.
SigGAN : Adversarial Model for Learning Signed Relationships in Networks
TLDR
A GAN based model for signed networks, SigGAN, inspired by the recent success of Generative Adversarial Network (GAN) based models in several applications is proposed and compared with state-of-the-art techniques on 5 real-world datasets validates the effectiveness of SigGAN.
Hyperparameter-free and Explainable Whole Graph Embedding
TLDR
A hyperparameterfree, extensible, and explainable whole graph embedding method combining the DHC (Degree, H-index and Coreness) theorem and Shannon Entropy (E), abbreviated as DHC-E is proposed, with promising potential for exploring graph classification, prediction, and lower-dimensional graph visualization.
...
...

References

SHOWING 1-10 OF 55 REFERENCES
Structural Deep Network Embedding
TLDR
This paper proposes a Structural Deep Network Embedding method, namely SDNE, which first proposes a semi-supervised deep model, which has multiple layers of non-linear functions, thereby being able to capture the highly non- linear network structure and exploits the first-order and second-order proximity jointly to preserve the network structure.
Deep Network Embedding with Aggregated Proximity Preserving
  • X. Shen, K. Chung
  • Computer Science
    2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
  • 2017
TLDR
With the hidden representations learned by DNE-APP, vector-based machine learning techniques are applied to conduct node classification and link label prediction tasks on the real-world datasets.
Deep Neural Networks for Learning Graph Representations
TLDR
A novel model for learning graph representations, which generates a low-dimensional vector representation for each vertex by capturing the graph structural information directly, and which outperforms other stat-of-the-art models in such tasks.
Signed Network Embedding in Social Media
TLDR
Experimental results on two realworld datasets of social media demonstrate the effectiveness of the proposed deep learning framework SiNE for signed network embedding that optimizes an objective function guided by social theories that provide a fundamental understanding of signed social networks.
Heterogeneous Network Embedding via Deep Architectures
TLDR
It is demonstrated that the rich content and linkage information in a heterogeneous network can be captured by a multi-resolution deep embedding function, so that similarities among cross-modal data can be measured directly in a common embedding space.
node2vec: Scalable Feature Learning for Networks
TLDR
In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.
LINE: Large-scale Information Network Embedding
TLDR
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.
Modularity Based Community Detection with Deep Learning
TLDR
This work proposes a novel nonlinear reconstruction method by adopting deep neural networks for representation and extends the method to a semi-supervised community detection algorithm by incorporating pairwise constraints among graph nodes.
Low rank modeling of signed networks
TLDR
It is shown that the notion of weak structural balance in signed networks naturally leads to a global low-rank model for the network, which can be used for other analysis tasks on signed networks, such as user segmentation through signed graph clustering, with theoretical guarantees.
Community mining in signed networks: A multiobjective approach
  • Alessia Amelio, C. Pizzuti
  • Computer Science
    2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2013)
  • 2013
TLDR
This paper proposes a multiobjective approach to detect communities in signed networks and shows that the maximization of signed modularity and the minimization of frustration allow to obtain very good solutions to the problem.
...
...