Simple Contrastive Graph Clustering

  title={Simple Contrastive Graph Clustering},
  author={Yue Liu and Xihong Yang and Sihang Zhou and Xinwang Liu},
Contrastive learning has recently attracted plenty of attention in deep graph clustering for its promising performance. However, complicated data augmentations and time-consuming graph convolutional operation undermine the efficiency of these methods. To solve this problem, we propose a Simple Contrastive Graph Clustering (SCGC) algorithm to improve the existing methods from the perspectives of network architecture, data augmentation, and objective function. As to the architecture, our network… 
1 Citations
Multiple Kernel Clustering with Dual Noise Minimization
This paper rigorously defines dual noise and proposes a novel parameter-free MKC algorithm that surpasses the recent methods by large margins and designs an efficient two-step iterative strategy to solve the resultant optimization problem.


Adversarially Regularized Graph Autoencoder for Graph Embedding
A novel adversarial graph embedding framework for graph data that encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure.
Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering
This work reformulates the GAE-based clustering methodology and proposes a sampling operator Ξ that triggers a protection mechanism against the noisy clustering assignments and an operator Υ that triggered a correction mechanism against Feature Drift by gradually transforming the reconstructed graph into a clustering-oriented one.
Simple Spectral Graph Convolution
This paper uses a modified Markov Diffusion Kernel to derive a variant of GCN called Simple Spectral Graph Convolution (S2GC), and spectral analysis shows that the simple spectral graph convolution used in S2GC is a trade-off of low and high-pass filter bands which capture the global and local contexts of each node.
Adaptive Graph Encoder for Attributed Graph Embedding
Experimental results show that AGE consistently outperforms state-of-the-art graph embedding methods considerably on node clustering and link prediction tasks, and the proposed Adaptive Graph Encoder employs an adaptive encoder that iteratively strengthens the filtered features for better node embeddings.
Learning Graph Embedding With Adversarial Training Methods
This article presents a novel adversarially regularized framework for graph embedding, employing the graph convolutional network as an encoder, that embeds the topological information and node content into a vector representation, from which a graph decoder is further built to reconstruct the input graph.
Algorithm AS 136: A k-means clustering algorithm
  • Journal of the royal statistical society. series c (applied statistics)
  • 1979
Deep Graph Clustering via Dual Correlation Reduction
This work proposes a novel self-supervised deep graph clustering method termed Dual Correlation Reduction Network (DCRN) by reducing information correlation in a dual manner and introduces a propagation regularization term to enable the network to gain long-distance information with the shallow network structure.
Multilayer Graph Contrastive Clustering Network
A generic and effective autoencoder framework for multilayer graph clustering named Multilayer Graph Contrastive Clustering Network (MGCCN), which employs a self-supervised component that iteratively strengthens the node embedding and clustering.
Self-supervised Contrastive Attributed Graph Clustering
This work proposes a novel attributed graph clustering network, namely Self-supervised Contrastive Attributed Graph Clustering (SCAGC), which consistently outperforms 11 competitive clustering methods.