Attributed Graph Clustering: A Deep Attentional Embedding Approach

By Chun Wang, Shirui Pan, Ruiqi Hu, Guodong Long, Jing Jiang, Chengqi Zhang. International Joint Conference on Artificial Intelligence, 2019

645 citations recorded by the source corpus.

Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods like k-means or spectral clustering algorithms are applied. These two-step frameworks are difficult to manipulate and usually lead to suboptimal performance, mainly because the graph embedding is not goal-directed, i.e., designed for the specific clustering task. In this paper, we propose a goal-directed deep learning approach, Deep Attentional Embedded Graph Clustering (DAEGC for short). Our method focuses on attributed graphs to sufficiently explore the two sides of information in graphs. By employing an attention network to capture the importance of the neighboring nodes to a target node, our DAEGC algorithm encodes the topological structure and node content in a graph to a compact representation, on which an inner product decoder is trained to reconstruct the graph structure. Furthermore, soft labels from the graph embedding itself are generated to supervise a self-training graph clustering process, which iteratively refines the clustering results. The self-training process is jointly learned and optimized with the graph embedding in a unified framework, to mutually benefit both components. Experimental results compared with state-of-the-art algorithms demonstrate the superiority of our method.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Transportation

View Paper: https://www.semanticscholar.org/paper/3c4d3ac27a23c144bb3c4f8785bffcdc71addd15

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philip S. Yu
2. Chuan Shi
3. Shirui Pan
4. Xiao Wang
5. Zhiyuan Liu
6. Jie Zhou
7. Peng Cui
8. Cheng Yang

In Statistical and Nonlinear Physics

1. Chuan Shi
2. Xiao Wang
3. Philip S. Yu
4. Shirui Pan
5. Peng Cui
6. Zhiyuan Liu
7. Cheng Yang
8. Jie Zhou

In Transportation

1. Peng Cui
2. Philip S. Yu
3. Chuan Shi
4. Xiao Wang
5. Deyu Bo
6. Quan Z. Sheng
7. Shirui Pan
8. Zhiyuan Liu

Citations in the corpus

• Deep Graph Clustering via Dual Correlation Reduction (2021, methodology): “In contrast, by reducing the information correlation in a dual manner, DCRN can learn more meaningful representation to improve the clustering performance; 2) it can be observed that the GCN-based clustering methods GAE/VGAE (Kipf and Welling 2016b), ARGA (Pan et al. 2019) and DAEGC (Wang et al. 201”
• A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning (2021, methodology): “Variational ARVGA (2018) [111] Yes Yes GCN Inner product Network embedding Prior constraint VGAECD (2018) [112] Yes Yes GCN Inner product Embedding and clustering DAEGC (2019) [113] Yes Yes GAT Inner product Embedding and Clustering KL divergence constraint New VGAECD (2019) [114] Yes Yes GCN Inner ”
• Adaptive Graph Encoder for Attributed Graph Embedding (2020, methodology): “DAEGC [31] employs Research Track Paper KDD '20, August 23–27, 2020, Virtual Event, USA”
• Structural Deep Clustering Network (2020, methodology): “• K -means [5]: A classical clustering method based on the • AE [7]: It is a two-stage deep clustering algorithm which performs K -means on the representations learned by autoen-coder • DEC [26]: It is a deep clustering method which designs a • IDEC [4]: This method adds a reconstruction loss to DEC”
• A Comprehensive Survey on Community Detection With Deep Learning (2021, background): “For example, deep attentional embedded graph clustering (DAEGC) [127] exploits high-order neighbors in an AE equipped with graph attention to cluster communities during a self-training process.”