Deep Attributed Network Embedding

Gao, Hongchang; Huang, Heng

doi:10.24963/ijcai.2018/467

Cited by 209 publications

(170 citation statements)

References 12 publications

Supporting

Mentioning

168

Contrasting

Order By: Relevance

“…As neither AN2VEC-0 nor AN2VEC-16 exhibited over-fitting, this behaviour is suprising and warrants further explorations which are beyond the scope of this paper (in particular, this may be specific to the link prediction task). Nonetheless, the higher performance of AN2VEC-S-0 and AN2VEC-S-16 over the vanilla VGAE on Cora and CiteSeer confirms that including feature reconstruction in the constraints of node embeddings is capable of increasing link prediction performance when feature and structure are not independent, and is consistent with [33,35,34]. An illustration of the embeddings produced by AN2VEC-S-16 on Cora is shown in Figure 4.…”

Section: Methodssupporting

confidence: 71%

“…In our model, different dimensions of the generated embeddings can be dedicated to encoding feature information, network structure, or shared feature-network information separately. Unlike previous embedding methods dealing with features [33,34,35,36], this interaction model [37] allows us to explore the dependencies between the disentangled network and feature information by comparing the embedding reconstruction performance to a baseline case where no shared information is extracted. Using this method, we can identify an optimal reduced embedding, which indicates whether combined information coming from the structure and features is important, or whether their non-interacting combination is sufficient for reconstructing the featured network.In practice, as this method solves a reconstruction problem, it may give important insights about the combination of feature-and structure-driven mechanisms which determine the formation of a given network.…”

mentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Methodssupporting

confidence: 71%

mentioning

confidence: 99%

Joint embedding of structure and features via graph convolutional networks

2020

View full text Add to dashboard Cite

show abstract

“…The training part of the model is implemented referring to the word2vec part of TensorFlow tutorials 8 . The evaluation part uses some metric functions from scikit-learn 9 including roc_auc_score, f1_score, preci-sion_recall_curve, auc. Our model parameters are updated and optimized by stochastic gradient descent with Adam updating rule [17].…”

Section: A1 Implementation Notesmentioning

confidence: 99%

Representation Learning for Attributed Multiplex Heterogeneous Network

Cen

Zou

Zhang

et al. 2019

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

348

199

View full text Add to dashboard Cite

Network embedding (or graph embedding) has been widely used in many real-world applications. However, existing methods mainly focus on networks with single-typed nodes/edges and cannot scale well to handle large networks. Many real-world networks consist of billions of nodes and edges of multiple types, and each node is associated with different attributes. In this paper, we formalize the problem of embedding learning for the Attributed Multiplex Heterogeneous Network and propose a unified framework to address this problem. The framework supports both transductive and inductive learning. We also give the theoretical analysis of the proposed framework, showing its connection with previous works and proving its better expressiveness. We conduct systematical evaluations for the proposed framework on four different genres of challenging datasets: Amazon, YouTube, Twitter, and Alibaba 1 . Experimental results demonstrate that with the learned embeddings from the proposed framework, we can achieve statistically significant improvements (e.g., 5.99-28.23% lift by F1 scores; p ≪ 0.01, t−test) over previous state-of-the-art methods for link prediction.The framework has also been successfully deployed on the recommendation system of a worldwide leading e-commerce company, Alibaba Group. Results of the offline A/B tests on product recommendation further confirm the effectiveness and efficiency of the framework in practice.

show abstract

“…In most studies, node attributes are only used for embedding initialization, but not during model training. DANE [4] proposes a deep non-linear architecture to preserve both aspects.…”

Section: Related Workmentioning

confidence: 99%

Robust Attribute and Structure Preserving Graph Embedding

Hettige

Wang

et al. 2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Graph embedding methods are useful for a wide range of graph analysis tasks including link prediction and node classification. Most graph embedding methods learn only the topological structure of graphs. Nevertheless, it has been shown that the incorporation of node attributes is beneficial in improving the expressive power of node embeddings. However, real-world graphs are often noisy in terms of structure and/or attributes (missing and/or erroneous edges/attributes). Most existing graph embedding methods are susceptible to this noise, as they do not consider uncertainty during the modelling process. In this paper, we introduce RASE, a Robust Attribute and Structure preserving graph Embedding model. RASE is a novel graph representation learning model which effectively preserves both graph structure and node attributes through a unified loss function. To be robust, RASE uses a denoising attribute auto-encoder to deal with node attribute noise, and models uncertainty in the embedding space as Gaussians to cope with graph structure noise. We evaluate the performance of RASE through an extensive experimental study on various real-world datasets. Results demonstrate that RASE outperforms state-of-the-art embedding methods on multiple graph analysis tasks and is robust to both structure and attribute noise.

show abstract

Deep Attributed Network Embedding

Cited by 209 publications

References 12 publications

Joint embedding of structure and features via graph convolutional networks

Joint embedding of structure and features via graph convolutional networks

Representation Learning for Attributed Multiplex Heterogeneous Network

Robust Attribute and Structure Preserving Graph Embedding

Contact Info

Product

Resources

About