ConstellationNet: Reinventing Spatial Clustering through GNNs

• URL: http://arxiv.org/abs/2503.07643v1
• Date: Thu, 06 Mar 2025 02:10:11 GMT
• Title: ConstellationNet: Reinventing Spatial Clustering through GNNs
• Authors: Aidan Gao, Junhong Lin,
• Abstract summary: We develop a convolution neural network(CNN)-graph neural network(GNN) framework that leverages the embedding power of a CNN, the neighbor aggregation of a GNN, and a neural network's ability to deal with batched data to improve spatial clustering and classification with graph augmented predictions.<n>ConstellationNet achieves state-of-the-art performance on both supervised classification and unsupervised clustering across several datasets, outperforming state-of-the-art classification and clustering while reducing model size and training time by up to tenfold.<n>Because of its fast training and powerful nature, ConstellationNet holds promise in fields like epidemiology and
• Score: 4.189643331553922
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Spatial clustering is a crucial field, finding universal use across criminology, pathology, and urban planning. However, most spatial clustering algorithms cannot pull information from nearby nodes and suffer performance drops when dealing with higher dimensionality and large datasets, making them suboptimal for large-scale and high-dimensional clustering. Due to modern data growing in size and dimension, clustering algorithms become weaker when addressing multifaceted issues. To improve upon this, we develop ConstellationNet, a convolution neural network(CNN)-graph neural network(GNN) framework that leverages the embedding power of a CNN, the neighbor aggregation of a GNN, and a neural network's ability to deal with batched data to improve spatial clustering and classification with graph augmented predictions. ConstellationNet achieves state-of-the-art performance on both supervised classification and unsupervised clustering across several datasets, outperforming state-of-the-art classification and clustering while reducing model size and training time by up to tenfold and improving baselines by 10 times. Because of its fast training and powerful nature, ConstellationNet holds promise in fields like epidemiology and medical imaging, able to quickly train on new data to develop robust responses.

Related papers

• ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion [15.33100217104504]
  This paper proposes a novel framework for large-scale graphs named ScaleGNN. It simultaneously addresses both challenges by adaptively fusing multi-level graph features. Our approach consistently outperforms state-of-the-art GNN models in both accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2025-04-22T14:05:11Z)
• The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks [0.716879432974126]
  Community detection is an essential tool for unsupervised data exploration and revealing the organisational structure of networked systems.<n>We consider the map equation, a popular information-theoretic objective function for unsupervised community detection, and express it in differentiable tensor form for gradient through descent.<n>Our formulation turns the map equation compatible with any neural network architecture, enables end-to-end learning, incorporates node features, and chooses the optimal number of clusters automatically.
  arXiv  Detail & Related papers  (2023-10-02T12:32:18Z)
• Adaptive Hierarchical SpatioTemporal Network for Traffic Forecasting [70.66710698485745]
  We propose an Adaptive Hierarchical SpatioTemporal Network (AHSTN) to promote traffic forecasting. AHSTN exploits the spatial hierarchy and modeling multi-scale spatial correlations. Experiments on two real-world datasets show that AHSTN achieves better performance over several strong baselines.
  arXiv  Detail & Related papers  (2023-06-15T14:50:27Z)
• 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)
• Deep Spatiotemporal Clustering: A Temporal Clustering Approach for Multi-dimensional Climate Data [0.353122873734926]
  We propose a novel algorithm for high-dimensional temporal representation of data using an unsupervised deep learning method. Inspired by U-net architecture, our algorithm utilizes an autoencoder integrating CNN-RNN layers to learn latent representations. Our experiments show our approach outperforms both conventional and deep learning-based unsupervised clustering algorithms.
  arXiv  Detail & Related papers  (2023-04-27T21:45:21Z)
• ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network [72.16255675586089]
  We propose an Adaptive Curvature Exploration Hyperbolic Graph NeuralNetwork named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability.
  arXiv  Detail & Related papers  (2021-10-15T07:18:57Z)
• Attention-driven Graph Clustering Network [49.040136530379094]
  We propose a novel deep clustering method named Attention-driven Graph Clustering Network (AGCN) AGCN exploits a heterogeneous-wise fusion module to dynamically fuse the node attribute feature and the topological graph feature. AGCN can jointly perform feature learning and cluster assignment in an unsupervised fashion.
  arXiv  Detail & Related papers  (2021-08-12T02:30:38Z)
• Augmented Data as an Auxiliary Plug-in Towards Categorization of Crowdsourced Heritage Data [2.609784101826762]
  We propose a strategy to mitigate the problem of inefficient clustering performance by introducing data augmentation as an auxiliary plug-in. We train a variant of Convolutional Autoencoder (CAE) with augmented data to construct the initial feature space as a novel model for deep clustering.
  arXiv  Detail & Related papers  (2021-07-08T14:09:39Z)
• Learning Hierarchical Graph Neural Networks for Image Clustering [81.5841862489509]
  We propose a hierarchical graph neural network (GNN) model that learns how to cluster a set of images into an unknown number of identities. Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level.
  arXiv  Detail & Related papers  (2021-07-03T01:28:42Z)
• Interpretable Clustering on Dynamic Graphs with Recurrent Graph Neural Networks [24.017988997693262]
  We study the problem of clustering nodes in a dynamic graph, where the connections between nodes and nodes' cluster memberships may change over time. We first propose a simple decay-based clustering algorithm that clusters nodes based on weighted connections between them, where the weight decreases at a fixed rate over time. We characterize the optimal decay rate for each cluster and propose a clustering method that achieves almost exact recovery of the true clusters.
  arXiv  Detail & Related papers  (2020-12-16T04:31:19Z)
• CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning [19.432449825536423]
  Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision. We present a novel cluster-aware graph neural network (CAGNN) model for unsupervised graph representation learning using self-supervised techniques.
  arXiv  Detail & Related papers  (2020-09-03T13:57:18Z)
• AM-GCN: Adaptive Multi-channel Graph Convolutional Networks [85.0332394224503]
  We study whether Graph Convolutional Networks (GCNs) can optimally integrate node features and topological structures in a complex graph with rich information. We propose an adaptive multi-channel graph convolutional networks for semi-supervised classification (AM-GCN) Our experiments show that AM-GCN extracts the most correlated information from both node features and topological structures substantially.
  arXiv  Detail & Related papers  (2020-07-05T08:16:03Z)

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.