MEGAN: A Generative Adversarial Network for Multi-View Network Embedding

Sun, Yiwei; Wang, Suhang; Hsieh, Tsung-Yu; Tang, Xianfeng; Honavar, Vasant

doi:10.24963/ijcai.2019/489

Cited by 28 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The skip-gram based models [14,30,37] combine random walk and the language model skip-gram [26] to learn embeddings. Compared with other deep learning based methods [36,42] and matrix factorization based methods [31,51], the skip-gram based ones often show faster, more scalable, and more stable ability. Graph neural networks are also widely used in node representation learning [16,19,40,41], while most of them rely on node attributes.…”

Section: Related Workmentioning

confidence: 99%

Contrastive Multi-View Multiplex Network Embedding with Applications to Robust Network Alignment

Xiong

Yan

Pan

2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Despite its success in learning network node representations, network embedding is still relatively new for multiplex networks (MNs) with multiple types of edges. In such networks, the inter-layer anchor links are usually missing, which represent the alignment relations between nodes on different layers and are a crucial prerequisite for many cross-network applications like network alignment. For mining such anchor links between layers for MNs, multiplex network embedding (MNE) has become one of the most promising techniques. In this paper, we consider two problems for MNs: 1) edges can be missing to different extent, and data augmentation may mitigate this issue; 2) the known alignment anchor links between layers can be misleading since the behaviors of nodes on different layers are not always consistent, so the most informative ones should be emphasized compared with those misleading ones. However, most existing works neglect the two problems and simply 1) adopt one structural view for all the layers (e.g. random walk with the same window size) and 2) equally extract information from all the anchor links. We propose an end-to-end contrastive framework called cM 2 NE for MNE, utilizing multiple structural views for each layer and learning with several plug-in components for different scenarios. Through end-to-end optimization on three levels, the intra-view, inter-view, and inter-layer level, our framework achieves to select the fitted views for different layers and maximize the inter-layer mutual information by emphasizing those most informative anchor links. Extensive experimental results on real-world datasets for node classification and multi-network alignment show that our approach consistently outperforms peer methods. CCS CONCEPTS• Information systems → Data mining.

show abstract

Section: Related Workmentioning

confidence: 99%

Contrastive Multi-View Multiplex Network Embedding with Applications to Robust Network Alignment

Xiong

Yan

Pan

2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

show abstract

“…Recently, generative adversarial networks (GANs) (Goodfellow et al 2014) have been widely applied to various domains (Yu et al 2017;Sun et al 2019;Shu et al 2018). Typical GAN consists of a generator and a discriminator.…”

Section: Adversarial Trainingmentioning

confidence: 99%

Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values

Tang

Yao

Sun

et al. 2020

AAAI

Self Cite

View full text Add to dashboard Cite

Multivariate time series (MTS) forecasting is widely used in various domains, such as meteorology and traffic. Due to limitations on data collection, transmission, and storage, real-world MTS data usually contains missing values, making it infeasible to apply existing MTS forecasting models such as linear regression and recurrent neural networks. Though many efforts have been devoted to this problem, most of them solely rely on local dependencies for imputing missing values, which ignores global temporal dynamics. Local dependencies/patterns would become less useful when the missing ratio is high, or the data have consecutive missing values; while exploring global patterns can alleviate such problem. Thus, jointly modeling local and global temporal dynamics is very promising for MTS forecasting with missing values. However, work in this direction is rather limited. Therefore, we study a novel problem of MTS forecasting with missing values by jointly exploring local and global temporal dynamics. We propose a new framework øurs, which leverages memory network to explore global patterns given estimations from local perspectives. We further introduce adversarial training to enhance the modeling of global temporal distribution. Experimental results on real-world datasets show the effectiveness of øurs for MTS forecasting with missing values and its robustness under various missing ratios.

show abstract

“…There are mainly two types of network representation learning methods: network embedding and graph neural networks. Network embedding is to embed network into a low dimensional space while preserving the network structure and property [9,31], such as random walk based methods [6], deep neural network models [21], matrix factorization based approaches [1,18]. For graph neural networks, GCN [12] is proposed to incorporate neighbors' features into the center node feature using convolutional operations.…”

Section: Related Workmentioning

confidence: 99%

Fast Attributed Multiplex Heterogeneous Network Embedding

Liu

Huang²,

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

In recent years, heterogeneous network representation learning has attracted considerable attentions with the consideration of multiple node types. However, most of them ignore the rich set of network attributes (attributed network) and different types of relations (multiplex network), which can hardly recognize the multimodal contextual signals across different relations. While a handful of network embedding techniques are developed for attributed multiplex heterogeneous networks, they are significantly limited to the scalability issue on large-scale network data, due to their heavy computation and memory cost. In this work, we propose a Fast Attributed Multiplex heterogeneous network Embedding framework (FAME) for large-scale network data, by mapping the units from different modalities (i.e., network topological structures, various node features and relations) into the same latent space in an efficient way. Our FAME is an integrative architecture with the scalable spectral transformation and sparse random projection, to automatically preserve both attribute semantics and multi-type relations in the learned embeddings. Extensive experiments on four real-world datasets with various network analytical tasks, demonstrate that FAME achieves both effectiveness and significant efficiency over state-of-the-art baselines. The source code is available at: https://github.com/ZhijunLiu95/FAME. CCS CONCEPTS • Mathematics of computing → Graph algorithms; • Computing methodologies → Learning latent representations.

show abstract

MEGAN: A Generative Adversarial Network for Multi-View Network Embedding

Cited by 28 publications

References 0 publications

Contrastive Multi-View Multiplex Network Embedding with Applications to Robust Network Alignment

Contrastive Multi-View Multiplex Network Embedding with Applications to Robust Network Alignment

Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values

Fast Attributed Multiplex Heterogeneous Network Embedding

Contact Info

Product

Resources

About