Graph Clustering via Variational Graph Embedding

2022 ◽  
Vol 122 ◽  
pp. 108334
Author(s):  
Lin Guo ◽  
Qun Dai
Keyword(s):  
Graph Embedding ◽  
Graph Clustering

scholarly journals Attributed Graph Clustering: A Deep Attentional Embedding Approach

2019 ◽  
Author(s):  
Chun Wang ◽  
Shirui Pan ◽  
Ruiqi Hu ◽  
Guodong Long ◽  
Jing Jiang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Graph Embedding ◽  
Graph Clustering ◽  
Inner Product ◽  
Compact Representation ◽  
Learning Approaches ◽  
Unified Framework ◽  
Attributed Graph ◽  
Attributed Graphs ◽  
Embedded Graph

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.

scholarly journals Variational Graph Embedding and Clustering with Laplacian Eigenmaps

2019 ◽  
Author(s):  
Zitai Chen ◽  
Chuan Chen ◽  
Zong Zhang ◽  
Zibin Zheng ◽  
Qingsong Zou
Keyword(s):  
Real World ◽  
Graph Embedding ◽  
Graph Clustering ◽  
Stochastic Gradient Descent ◽  
Laplacian Eigenmaps ◽  
Generative Process ◽  
Clustering Problem ◽  
Teacher Student ◽  
Mixture Of Gaussian ◽  
Node Embeddings

As a fundamental machine learning problem, graph clustering has facilitated various real-world applications, and tremendous efforts had been devoted to it in the past few decades. However, most of the existing methods like spectral clustering suffer from the sparsity, scalability, robustness and handling high dimensional raw information in clustering. To address this issue, we propose a deep probabilistic model, called Variational Graph Embedding and Clustering with Laplacian Eigenmaps (VGECLE), which learns node embeddings and assigns node clusters simultaneously. It represents each node as a Gaussian distribution to disentangle the true embedding position and the uncertainty from the graph. With a Mixture of Gaussian (MoG) prior, VGECLE is capable of learning an interpretable clustering by the variational inference and generative process. In order to learn the pairwise relationships better, we propose a Teacher-Student mechanism encouraging node to learn a better Gaussian from its instant neighbors in the stochastic gradient descent (SGD) training fashion. By optimizing the graph embedding and the graph clustering problem as a whole, our model can fully take the advantages in their correlation. To our best knowledge, we are the first to tackle graph clustering in a deep probabilistic viewpoint. We perform extensive experiments on both synthetic and real-world networks to corroborate the effectiveness and efficiency of the proposed framework.

An Efficient Method for Attributed Graph Clustering

2014 ◽  
Vol 36 (8) ◽  
pp. 1704-1713 ◽  
Author(s):  
Ye WU ◽  
Zhi-Nong ZHONG ◽  
Wei XIONG ◽  
Luo CHEN ◽  
Ning JING
Keyword(s):  
Efficient Method ◽  
Graph Clustering ◽  
Attributed Graph

A Transition-Based Knowledge Graph Embedding with Adapting New Entities

2016 ◽  
Author(s):  
A-Yeong Kim ◽  
◽  
Hee-Guen Yoon ◽  
Seong-Bae Park ◽  
Se-Young Park ◽  
...  
Keyword(s):  
Graph Embedding ◽  
Knowledge Graph

scholarly journals Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art

2021 ◽  
Author(s):  
Yun Peng ◽  
Byron Choi ◽  
Jianliang Xu
Keyword(s):  
Machine Learning ◽  
Combinatorial Optimization ◽  
Graph Embedding ◽  
Partial Solution ◽  
Complex Data ◽  
Learning Methods ◽  
Graph Learning ◽  
Second Stage ◽  
End To End ◽  
Embedding Methods

AbstractGraphs have been widely used to represent complex data in many applications, such as e-commerce, social networks, and bioinformatics. Efficient and effective analysis of graph data is important for graph-based applications. However, most graph analysis tasks are combinatorial optimization (CO) problems, which are NP-hard. Recent studies have focused a lot on the potential of using machine learning (ML) to solve graph-based CO problems. Most recent methods follow the two-stage framework. The first stage is graph representation learning, which embeds the graphs into low-dimension vectors. The second stage uses machine learning to solve the CO problems using the embeddings of the graphs learned in the first stage. The works for the first stage can be classified into two categories, graph embedding methods and end-to-end learning methods. For graph embedding methods, the learning of the the embeddings of the graphs has its own objective, which may not rely on the CO problems to be solved. The CO problems are solved by independent downstream tasks. For end-to-end learning methods, the learning of the embeddings of the graphs does not have its own objective and is an intermediate step of the learning procedure of solving the CO problems. The works for the second stage can also be classified into two categories, non-autoregressive methods and autoregressive methods. Non-autoregressive methods predict a solution for a CO problem in one shot. A non-autoregressive method predicts a matrix that denotes the probability of each node/edge being a part of a solution of the CO problem. The solution can be computed from the matrix using search heuristics such as beam search. Autoregressive methods iteratively extend a partial solution step by step. At each step, an autoregressive method predicts a node/edge conditioned to current partial solution, which is used to its extension. In this survey, we provide a thorough overview of recent studies of the graph learning-based CO methods. The survey ends with several remarks on future research directions.

Sign in / Sign up

Export Citation Format

Share Document