Attributed Graph Clustering: A Deep Attentional Embedding Approach

Wang, Chun; Pan, Shirui; Hu, Ruiqi; Long, Guodong; Jiang, Jing; Zhang, Chengqi

doi:10.24963/ijcai.2019/509

Cited by 333 publications

(187 citation statements)

References 1 publication

Supporting

Mentioning

167

Contrasting

Unclassified

Order By: Relevance

“…As for the GCN-based methods, we set the dimension of GAE and VAGE to d-256-16 and train them with 30 epochs for all datasets. For DAEGC, we use the setting of [25]. In hyperparameter search, we try {1, 3, 5} for the update interval in DEC and IDEC, {1, 0.1, 0.01, 0.001} for the hyperparameter γ in IDEC and report the best results.…”

Section: Baselinesmentioning

confidence: 99%

Structural Deep Clustering Network

Xiao

Shi

et al. 2020

Proceedings of the Web Conference 2020

335

235

View full text Add to dashboard Cite

Clustering is a fundamental task in data analysis. Recently, deep clustering, which derives inspiration primarily from deep learning approaches, achieves state-of-the-art performance and has attracted considerable attention. Current deep clustering methods usually boost the clustering results by means of the powerful representation ability of deep learning, e.g., autoencoder, suggesting that learning an effective representation for clustering is a crucial requirement. The strength of deep clustering methods is to extract the useful representations from the data itself, rather than the structure of data, which receives scarce attention in representation learning. Motivated by the great success of Graph Convolutional Network (GCN) in encoding the graph structure, we propose a Structural Deep Clustering Network (SDCN) to integrate the structural information into deep clustering. Specifically, we design a delivery operator to transfer the representations learned by autoencoder to the corresponding GCN layer, and a dual self-supervised mechanism to unify these two different deep neural architectures and guide the update of the whole model. In this way, the multiple structures of data, from low-order to high-order, are naturally combined with the multiple representations learned by autoencoder. Furthermore, we theoretically analyze the delivery operator, i.e., with the delivery operator, GCN improves the autoencoder-specific representation as a high-order graph regularization constraint and autoencoder helps alleviate the over-smoothing problem in GCN. Through comprehensive experiments, we demonstrate that our propose model can consistently perform better over the state-of-the-art techniques.

show abstract

Section: Baselinesmentioning

confidence: 99%

Structural Deep Clustering Network

Xiao

Shi

et al. 2020

Proceedings of the Web Conference 2020

335

235

View full text Add to dashboard Cite

show abstract

“…DAEGC. Deep Attentional Embedded Graph Clustering DAEGC [202], in opposite to the embeddings-based early fusion methods, uses a goal-directed deep learning approach with a unified framework for producing embeddings and clustering. Namely, DAEGC fuses network topology and semantics via an attentional autoencoder (a variant of the graph attention network [200] taking into account high-order proximity) to obtain node embeddings.…”

Section: Simultaneous Fusion Methodsmentioning

confidence: 99%

Community Detection in Attributed Social Networks: A Unified Weight-Based Model and Its Regimes

Chunaev

Nuzhdenko

Bochenina

2019

2019 International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

Community detection is a fundamental problem in social network analysis consisting, roughly speaking, in dividing social actors (modelled as nodes in a social graph) with certain social connections (modelled as edges in the social graph) into densely knitted and highly related groups with each group well separated from the others. Classical approaches for community detection usually deal only with the structure of the network and ignore features of the nodes, although major real-world networks provide additional actors' information such as age, gender, interests, etc., traditionally called node attributes. It is known that the attributes may clarify and enrich the knowledge about the actors and give sense to the detected communities. This has led to a relatively novel direction in community detection -constructing algorithms that use both the structure and the attributes of the network (modelled already via a nodeattributed graph) to yield more informative and qualitative results.During the last decade many methods based on different ideas and techniques have appeared in this direction. Although there exist some partial overviews of them, a recent survey is a necessity as the growing number of the methods may cause uncertainty in practice.In this paper we aim at clarifying the overall situation by proposing a clear classification of the methods and providing a comprehensive survey of the available results. We not only group and analyse the corresponding methods but also focus on practical aspects, including the information which methods outperform others and which datasets and quality measures are used for evaluation.

show abstract

“…As variants of GAE (VGAE), [23] exploits adversarially regularized method to learn more robust node embeddings. [31] further employs graph attention networks [30] to differentiate the importance of the neighboring nodes to a target node.…”

Section: Gcn-based Graph Embeddingmentioning

confidence: 99%

“…It has been proved that the range of Laplacian eigenvalues is between 0 and 2 [7], hence GCN filter is not low-pass in the (1,2] interval. Some work [31] accordingly chooses k = 1/2. However, our experiments show that after renormalization, the maximum eigenvalue λ max will shrink to around 3/2, which makes 1/2 not optimal as well.…”

Section: 33mentioning

confidence: 99%

Adaptive Graph Encoder for Attributed Graph Embedding

Cui

Zhou

Yang

et al. 2020

Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

162

View full text Add to dashboard Cite

Attributed graph embedding, which learns vector representations from graph topology and node features, is a challenging task for graph analysis. Recently, methods based on graph convolutional networks (GCNs) have made great progress on this task. However, existing GCN-based methods have three major drawbacks. Firstly, our experiments indicate that the entanglement of graph convolutional filters and weight matrices will harm both the performance and robustness. Secondly, we show that graph convolutional filters in these methods reveal to be special cases of generalized Laplacian smoothing filters, but they do not preserve optimal low-pass characteristics. Finally, the training objectives of existing algorithms are usually recovering the adjacency matrix or feature matrix, which are not always consistent with real-world applications. To address these issues, we propose Adaptive Graph Encoder (AGE), a novel attributed graph embedding framework. AGE consists of two modules: (1) To better alleviate the high-frequency noises in the node features, AGE first applies a carefully-designed Laplacian smoothing filter. (2) AGE employs an adaptive encoder that iteratively strengthens the filtered features for better node embeddings. We conduct experiments using four public benchmark datasets to validate AGE on node clustering and link prediction tasks. Experimental results show that AGE consistently outperforms state-of-the-art graph embedding methods considerably on these tasks.

show abstract

Attributed Graph Clustering: A Deep Attentional Embedding Approach

Cited by 333 publications

References 1 publication

Structural Deep Clustering Network

Structural Deep Clustering Network

Community Detection in Attributed Social Networks: A Unified Weight-Based Model and Its Regimes

Adaptive Graph Encoder for Attributed Graph Embedding

Contact Info

Product

Resources

About