Deep Graph Clustering via Mutual Information Maximization and Mixture Model

• URL: http://arxiv.org/abs/2205.05168v1
• Date: Tue, 10 May 2022 21:03:55 GMT
• Title: Deep Graph Clustering via Mutual Information Maximization and Mixture Model
• Authors: Maedeh Ahmadi, Mehran Safayani, Abdolreza Mirzaei
• Abstract summary: We introduce a contrastive learning framework for learning clustering-friendly node embedding. Experiments on real-world datasets demonstrate the effectiveness of our method in community detection.
• Score: 6.488575826304023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Attributed graph clustering or community detection which learns to cluster the nodes of a graph is a challenging task in graph analysis. In this paper, we introduce a contrastive learning framework for learning clustering-friendly node embedding. Although graph contrastive learning has shown outstanding performance in self-supervised graph learning, using it for graph clustering is not well explored. We propose Gaussian mixture information maximization (GMIM) which utilizes a mutual information maximization approach for node embedding. Meanwhile, it assumes that the representation space follows a Mixture of Gaussians (MoG) distribution. The clustering part of our objective tries to fit a Gaussian distribution to each community. The node embedding is jointly optimized with the parameters of MoG in a unified framework. Experiments on real-world datasets demonstrate the effectiveness of our method in community detection.

Related papers

• Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective [44.4638436277021]
  We propose a community-aware graph clustering framework, MAGI, which leverages modularity coined as a contrastive pretext task. We show strong connections between modularity and graph contrastive learning, where positive and negative examples are naturally defined by modularity. In light of our results, we propose a community-aware graph clustering framework, MAGI, which leverages modularity coined as a contrastive pretext task.
  arXiv  Detail & Related papers  (2024-06-20T13:14:44Z)
• Cluster-based Graph Collaborative Filtering [55.929052969825825]
  Graph Convolution Networks (GCNs) have succeeded in learning user and item representations for recommendation systems. Most existing GCN-based methods overlook the multiple interests of users while performing high-order graph convolution. We propose a novel GCN-based recommendation model, termed Cluster-based Graph Collaborative Filtering (ClusterGCF)
  arXiv  Detail & Related papers  (2024-04-16T07:05:16Z)
• DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization [5.329981192545312]
  We propose a novel method, DGCluster, which primarily optimize the modularity objective using graph neural networks and scales linearly with the graph size. We extensively test DGCluster on several real-world datasets of varying sizes, across multiple popular cluster quality metrics. Our approach consistently outperforms the state-of-the-art methods, demonstrating significant performance gains in almost all settings.
  arXiv  Detail & Related papers  (2023-12-20T01:43:55Z)
• Reinforcement Graph Clustering with Unknown Cluster Number [91.4861135742095]
  We propose a new deep graph clustering method termed Reinforcement Graph Clustering. In our proposed method, cluster number determination and unsupervised representation learning are unified into a uniform framework. In order to conduct feedback actions, the clustering-oriented reward function is proposed to enhance the cohesion of the same clusters and separate the different clusters.
  arXiv  Detail & Related papers  (2023-08-13T18:12:28Z)
• Dink-Net: Neural Clustering on Large Graphs [59.10189693120368]
  A deep graph clustering method (Dink-Net) is proposed with the idea of dilation and shrink. By discriminating nodes, whether being corrupted by augmentations, representations are learned in a self-supervised manner. The clustering distribution is optimized by minimizing the proposed cluster dilation loss and cluster shrink loss. Compared to the runner-up, Dink-Net 9.62% achieves NMI improvement on the ogbn-papers100M dataset with 111 million nodes and 1.6 billion edges.
  arXiv  Detail & Related papers  (2023-05-28T15:33:24Z)
• Learning Optimal Graph Filters for Clustering of Attributed Graphs [20.810096547938166]
  Many real-world systems can be represented as graphs where the different entities in the system are presented by nodes and their interactions by edges. An important task in studying large datasets with graphical structure is graph clustering. We introduce a graph signal processing based approach, where we learn the parameters of Finite Impulse Response (FIR) and Autoregressive Moving Average (ARMA) graph filters optimized for clustering.
  arXiv  Detail & Related papers  (2022-11-09T01:49:23Z)
• Data-heterogeneity-aware Mixing for Decentralized Learning [63.83913592085953]
  We characterize the dependence of convergence on the relationship between the mixing weights of the graph and the data heterogeneity across nodes. We propose a metric that quantifies the ability of a graph to mix the current gradients. Motivated by our analysis, we propose an approach that periodically and efficiently optimize the metric.
  arXiv  Detail & Related papers  (2022-04-13T15:54:35Z)
• Fine-grained Graph Learning for Multi-view Subspace Clustering [2.4094285826152593]
  We propose a fine-grained graph learning framework for multi-view subspace clustering (FGL-MSC) The main challenge is how to optimize the fine-grained fusion weights while generating the learned graph that fits the clustering task. Experiments on eight real-world datasets show that the proposed framework has comparable performance to the state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-01-12T18:00:29Z)
• Graph Representation Learning via Contrasting Cluster Assignments [57.87743170674533]
  We propose a novel unsupervised graph representation model by contrasting cluster assignments, called as GRCCA. It is motivated to make good use of local and global information synthetically through combining clustering algorithms and contrastive learning. GRCCA has strong competitiveness in most tasks.
  arXiv  Detail & Related papers  (2021-12-15T07:28:58Z)
• Effective and Efficient Graph Learning for Multi-view Clustering [173.8313827799077]
  We propose an effective and efficient graph learning model for multi-view clustering. Our method exploits the view-similar between graphs of different views by the minimization of tensor Schatten p-norm. Our proposed algorithm is time-economical and obtains the stable results and scales well with the data size.
  arXiv  Detail & Related papers  (2021-08-15T13:14:28Z)
• Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning [12.592903558338444]
  We propose a graph representation learning method called Graph InfoClust. It seeks to additionally capture cluster-level information content. This optimization leads the node representations to capture richer information and nodal interactions, which improves their quality.
  arXiv  Detail & Related papers  (2020-09-15T09:33:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.