Deep Variational Network Embedding in Wasserstein Space

Zhu, Dingyuan; Cui, Peng; Wang, Daixin; Zhu, Wenwu

doi:10.1145/3219819.3220052

Cited by 128 publications

(84 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both methods show that capturing embedding uncertainty learns more meaningful representations in their evaluation tasks. Another recent study [17] proposes to learn node embeddings as Gaussian distributions using the Wasserstein metric rather than KL divergence, as the former preserves edge transitivity.…”

Section: Related Workmentioning

confidence: 99%

Gaussian Embedding of Large-Scale Attributed Graphs

Hettige

Wang

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification, recommendation and visualization. Most existing approaches represent graph nodes as point vectors in a low-dimensional embedding space, ignoring the uncertainty present in the real-world graphs. Furthermore, many real-world graphs are large-scale and rich in content (e.g. node attributes). In this work, we propose GLACE, a novel, scalable graph embedding method that preserves both graph structure and node attributes effectively and efficiently in an end-to-end manner. GLACE effectively models uncertainty through Gaussian embeddings, and supports inductive inference of new nodes based on their attributes. In our comprehensive experiments, we evaluate GLACE on real-world graphs, and the results demonstrate that GLACE significantly outperforms stateof-the-art embedding methods on multiple graph analysis tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Gaussian Embedding of Large-Scale Attributed Graphs

Hettige

Wang

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…It can benefit a variety of tasks including recommendation. Many effective network embedding algorithms have been proposed [10,15,17,19,25]. We briefly review some of these methods here.…”

Section: Related Work 21 Network Embeddingmentioning

confidence: 99%

“…SDNE [19] exploited the first-order proximity and secondorder proximity in a joint approach to capture both the local and global network structure. DVNE [25] learned a Gaussian distribution in the Wasserstein space for each node to preserve more properties such as transitivity and uncertainty.…”

Section: Related Work 21 Network Embeddingmentioning

confidence: 99%

IntentGC

Zhao

Zhou

Guan

et al. 2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

123

View full text Add to dashboard Cite

The remarkable progress of network embedding has led to stateof-the-art algorithms in recommendation. However, the sparsity of user-item interactions (i.e., explicit preferences) on websites remains a big challenge for predicting users' behaviors. Although research efforts have been made in utilizing some auxiliary information (e.g., social relations between users) to solve the problem, the existing rich heterogeneous auxiliary relationships are still not fully exploited. Moreover, previous works relied on linearly combined regularizers and suffered parameter tuning.In this work, we collect abundant relationships from common user behaviors and item information, and propose a novel framework named IntentGC to leverage both explicit preferences and heterogeneous relationships by graph convolutional networks. In addition to the capability of modeling heterogeneity, IntentGC can learn the importance of different relationships automatically by the neural model in a nonlinear sense. To apply IntentGC to webscale applications, we design a faster graph convolutional model named IntentNet by avoiding unnecessary feature interactions. Empirical experiments on two large-scale real-world datasets and online A/B tests in Alibaba demonstrate the superiority of our method over state-of-the-art algorithms.

show abstract

“…Their development would offer huge potential in understanding the relation between individuals' characters, their social relationships, the content they are engaged with, and the larger communities they belong to. This would not only provide us with deeper insight about social behaviour, it would give us predictive tools for the emergence of network structure, individual interests and behavioural patterns.In this paper we propose a contribution to solving this problem by developing a joint featurenetwork embedding built on multitask Graph Convolutional Networks [24,25,26,27] and Variational Autoencoders (GCN-VAE) [28,29,30,31,32], which we call the Attributed Network to Vector method (AN2VEC). In our model, different dimensions of the generated embeddings can be dedicated to encoding feature information, network structure, or shared feature-network information separately.…”

mentioning

confidence: 99%

Joint embedding of structure and features via graph convolutional networks

2020

View full text Add to dashboard Cite

The creation of social ties is largely determined by the entangled effects of people's similarities in terms of individual characters and friends. However, feature and structural characters of people usually appear to be correlated, making it difficult to determine which has greater responsibility in the formation of the emergent network structure. We propose AN2VEC, a node embedding method which ultimately aims at disentangling the information shared by the structure of a network and the features of its nodes. Building on the recent developments of Graph Convolutional Networks (GCN), we develop a multitask GCN Variational Autoencoder where different dimensions of the generated embeddings can be dedicated to encoding feature information, network structure, and shared feature-network information. We explore the interaction between these disentangled characters by comparing the embedding reconstruction performance to a baseline case where no shared information is extracted. We use synthetic datasets with different levels of interdependency between feature and network characters and show (i) that shallow embeddings relying on shared information perform better than the corresponding reference with unshared information, (ii) that this performance gap increases with the correlation between network and feature structure, and (iii) that our embedding is able to capture joint information of structure and features. Our method can be relevant for the analysis and prediction of any featured network structure ranging from online social systems to network medicine. communities of shared interest, age, gender, or socio-economic status, and so on [4,12]. Though these mechanisms are not independent and lead to correlations between feature and network communities, it is difficult to define the causal relationship between the two: first, because simultaneously characterising similarities between multiple features and a complex network structure is not an easy task; second, because it is difficult to determine which of the two types of information, features or structure, is driving network formation to a greater extent. Indeed, we do not know what fraction of similar people initially get connected through homophilic tie creation, versus the fraction that first get connected due to structural similarities before influencing each other to become more similar [13,14].Over the last decade popular methods have been developed to characterise structural and feature similarities and to identify these two notions of communities. The detection of network communities has been a major challenge in network science with various concepts proposed [15,16,17] to solve it as an unsupervised learning task [18,19]. Commonly, these algorithms rely solely on network information, and their output is difficult to cross-examine without additional meta-data which is usually disregarded in their description. On the other hand, methods grouping similar people into feature communities typically ignore network information, and exclusively rely on individual feat...

show abstract

Deep Variational Network Embedding in Wasserstein Space

Cited by 128 publications

References 20 publications

Gaussian Embedding of Large-Scale Attributed Graphs

Gaussian Embedding of Large-Scale Attributed Graphs

IntentGC

Joint embedding of structure and features via graph convolutional networks

Contact Info

Product

Resources

About