• Corpus ID: 220265535

Graph Clustering with Graph Neural Networks

  title={Graph Clustering with Graph Neural Networks},
  author={Anton Tsitsulin and John Palowitch and Bryan Perozzi and Emmanuel M{\"u}ller},
Graph Neural Networks (GNNs) have achieved state-of-the-art results on many graph analysis tasks such as node classification and link prediction. However, important unsupervised problems on graphs, such as graph clustering, have proved more resistant to advances in GNNs. In this paper, we study unsupervised training of GNN pooling in terms of their clustering capabilities. We start by drawing a connection between graph clustering and graph pooling: intuitively, a good graph clustering is what… 

Figures and Tables from this paper

Higher-order Clustering and Pooling for Graph Neural Networks

This work proposes HoscPool, a clustering-based graph pooling operator that captures higher-order information hierarchically, leading to richer graph representations and provides a deep empirical analysis of pooling operators' inner functioning.

Efficient Graph Convolution for Joint Node Representation Learning and Clustering

A model based on a variant of the simple graph convolutional network does clustering by minimizing the difference between the convolved node representations and their reconstructed cluster representatives, and demonstrates the usefulness of the proposed approach for graph visualization through generating embeddings that exhibit a clustering structure.

Graph Structure Estimation Neural Networks

The proposed graph estimation neural networks GEN presents a structure model to fit the mechanism of GNNs by generating graphs with community structure, and an observation model that injects multifaceted observations into calculating the posterior distribution of graphs and is the first to incorporate multi-order neighborhood information.

Synthetic Graph Generation to Benchmark Graph Learning

This work develops a fully-featured synthetic graph generator that allows deep inspection of different models and argues that synthetic graph generations allows for thorough investigation of algorithms and provides more insights than overfitting on three citation datasets.

Machine Learning on Graphs: A Model and Comprehensive Taxonomy

A comprehensive taxonomy of representation learning methods for graph-structured data is proposed, aiming to unify several disparate bodies of work and provide a solid foundation for understanding the intuition behind these methods, and enables future research in the area.

Graph neural network inspired algorithm for unsupervised network community detection

A new variant of the recurrent graph neural network algorithm for unsupervised network community detection through modularity optimization is proposed and its performance is compared against the state-of-the-art methods.

Amortized Probabilistic Detection of Communities in Graphs

This work proposes a simple framework for amortized community detection, which addresses both of these issues by combining the expressive power of GNNs with recent methods forAmortized clustering, and evaluates several models from this framework on synthetic and real datasets and demonstrates superior performance.

CGC: Contrastive Graph Clustering forCommunity Detection and Tracking

This work develops CGC, a novel end-to-end framework for graph clustering, which fundamentally differs from existing methods, and extends CGC for time-evolving data, where temporalgraph clustering is performed in an incremental learning fashion, with the ability to detect change points.

Shift-Robust Node Classification via Graph Clustering Co-training

This work proposes SRNC - a unified domain adaptation framework for different kinds of distribution shifts on graph that works for both open-set and close-set shifts with convergence guarantees and is able to mitigate the negative effect of the shift across different testing-times.

Adaptive Harmony Learning and Optimization for Attributed Graph Clustering

A novel method named Adaptive Harmony Learning and Optimization for attributed graph clustering, which models the node embeddings with the mixture of von Mises-Fisher distributions on the unit hypersphere and develops an alternating learning strategy that can simultaneously improve the intra-clusters compactness and inter-cluster separability.



Spectral Clustering with Graph Neural Networks for Graph Pooling

This paper forms a continuous relaxation of the normalized minCUT problem and trains a GNN to compute cluster assignments that minimize this objective, and designs a graph pooling operator that overcomes some important limitations of state-of-the-art graph Pooling techniques and achieves the best performance in several supervised and unsupervised tasks.

Hierarchical Graph Representation Learning with Differentiable Pooling

DiffPool is proposed, a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion.

Pitfalls of Graph Neural Network Evaluation

This paper performs a thorough empirical evaluation of four prominent GNN models and suggests that simpler GNN architectures are able to outperform the more sophisticated ones if the hyperparameters and the training procedure are tuned fairly for all models.

Machine Learning on Graphs: A Model and Comprehensive Taxonomy

A comprehensive taxonomy of representation learning methods for graph-structured data is proposed, aiming to unify several disparate bodies of work and provide a solid foundation for understanding the intuition behind these methods, and enables future research in the area.

Attributed Graph Clustering: A Deep Attentional Embedding Approach

This paper proposes a goal-directed deep learning approach to graph clustering, Deep Attentional Embedded Graph Clustering (DAEGC), which focuses on attributed graphs to sufficiently explore the two sides of information in graphs.

Attributed Graph Clustering via Adaptive Graph Convolution

This paper proposes an adaptive graph convolution method for attributed graph clustering that exploits high-ordergraph convolution to capture global cluster structure and adaptively selects the appropriate order for different graphs.

Position-aware Graph Neural Networks

Position-aware Graph Neural Networks (P-GNNs) are proposed, a new class of GNNs for computing position-aware node embeddings that are inductive, scalable, and can incorporate node feature information.

Benchmarking Graph Neural Networks

A reproducible GNN benchmarking framework is introduced, with the facility for researchers to add new models conveniently for arbitrary datasets, and a principled investigation into the recent Weisfeiler-Lehman GNNs (WL-GNNs) compared to message passing-based graph convolutional networks (GCNs).

Graph Attention Networks

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior

Representation Learning on Graphs: Methods and Applications

A conceptual review of key advancements in this area of representation learning on graphs, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks are provided.