Inferring the Graph Structure of Images for Graph Neural Networks

• URL: http://arxiv.org/abs/2509.04677v1
• Date: Thu, 04 Sep 2025 21:41:59 GMT
• Title: Inferring the Graph Structure of Images for Graph Neural Networks
• Authors: Mayur S Gowda, John Shi, Augusto Santos, José M. F. Moura,
• Abstract summary: We improve the accuracy of downstream graph neural network tasks by finding alternative graphs to the grid graph and superpixel methods.<n>Experiments show that using these different graph representations and features as input into downstream GNN models improves the accuracy over using the traditional grid graph and superpixel methods in the literature.
• Score: 13.364838409095361
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image datasets such as MNIST are a key benchmark for testing Graph Neural Network (GNN) architectures. The images are traditionally represented as a grid graph with each node representing a pixel and edges connecting neighboring pixels (vertically and horizontally). The graph signal is the values (intensities) of each pixel in the image. The graphs are commonly used as input to graph neural networks (e.g., Graph Convolutional Neural Networks (Graph CNNs) [1, 2], Graph Attention Networks (GAT) [3], GatedGCN [4]) to classify the images. In this work, we improve the accuracy of downstream graph neural network tasks by finding alternative graphs to the grid graph and superpixel methods to represent the dataset images, following the approach in [5, 6]. We find row correlation, column correlation, and product graphs for each image in MNIST and Fashion-MNIST using correlations between the pixel values building on the method in [5, 6]. Experiments show that using these different graph representations and features as input into downstream GNN models improves the accuracy over using the traditional grid graph and superpixel methods in the literature.

Related papers

• ViG-LRGC: Vision Graph Neural Networks with Learnable Reparameterized Graph Construction [0.15293427903448023]
  Vision Graph Neural Networks (ViG) have proposed the treatment of images as a graph of nodes.<n>The challenge is to construct a graph of nodes in each layer that best represents the relations between nodes.<n>We present the Learnable Reparameterized Graph Construction (LRGC) for Vision Graph Neural Networks.<n>We demonstrate that the proposed ViG-LRGC approach outperforms state-of-the-art ViG models of similar sizes on the ImageNet-1k benchmark dataset.
  arXiv  Detail & Related papers  (2025-09-23T09:25:22Z)
• Pixel-wise Graph Attention Networks for Person Re-identification [18.662170017063286]
  Graph convolutional networks (GCN) is widely used to handle irregular data. How to apply GCN to structured data (such as pictures) has not been deeply studied. In this paper, we explore the application of graph attention networks (GAT) in image feature extraction.
  arXiv  Detail & Related papers  (2023-07-18T12:12:42Z)
• Graph Mixup with Soft Alignments [49.61520432554505]
  We study graph data augmentation by mixup, which has been used successfully on images. We propose S-Mixup, a simple yet effective mixup method for graph classification by soft alignments.
  arXiv  Detail & Related papers  (2023-06-11T22:04:28Z)
• Image Keypoint Matching using Graph Neural Networks [22.33342295278866]
  We propose a graph neural network for the problem of image matching. The proposed method first generates initial soft correspondences between keypoints using localized node embeddings. We evaluate our method on natural image datasets with keypoint annotations and show that, in comparison to a state-of-the-art model, our method speeds up inference times without sacrificing prediction accuracy.
  arXiv  Detail & Related papers  (2022-05-27T23:38:44Z)
• KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification [13.419578861488226]
  We propose a Kernel-based Graph Neural Network (KGNN) for semi-supervised graph classification. We show that KGNN achieves impressive performance over competitive baselines.
  arXiv  Detail & Related papers  (2022-05-21T10:03:46Z)
• BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Network [35.97496022085212]
  Many graph convolutional networks can be regarded as low-pass filters for graph signals. We propose a new model, BiGCN, which represents a graph neural network as a bi-directional low-pass filter. Our model outperforms previous graph neural networks in the tasks of node classification and link prediction on most of the benchmark datasets.
  arXiv  Detail & Related papers  (2021-01-14T09:41:00Z)
• Line Graph Neural Networks for Link Prediction [71.00689542259052]
  We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications. In this formalism, a link prediction problem is converted to a graph classification task. We propose to seek a radically different and novel path by making use of the line graphs in graph theory. In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task.
  arXiv  Detail & Related papers  (2020-10-20T05:54:31Z)
• Multilevel Graph Matching Networks for Deep Graph Similarity Learning [79.3213351477689]
  We propose a multi-level graph matching network (MGMN) framework for computing the graph similarity between any pair of graph-structured objects. To compensate for the lack of standard benchmark datasets, we have created and collected a set of datasets for both the graph-graph classification and graph-graph regression tasks. Comprehensive experiments demonstrate that MGMN consistently outperforms state-of-the-art baseline models on both the graph-graph classification and graph-graph regression tasks.
  arXiv  Detail & Related papers  (2020-07-08T19:48:19Z)
• Graph Pooling with Node Proximity for Hierarchical Representation Learning [80.62181998314547]
  We propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Results show that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-19T13:09:44Z)
• Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks [183.97265247061847]
  We leverage graph signal processing to characterize the representation space of graph neural networks (GNNs) We discuss the role of graph convolutional filters in GNNs and show that any architecture built with such filters has the fundamental properties of permutation equivariance and stability to changes in the topology. We also study the use of GNNs in recommender systems and learning decentralized controllers for robot swarms.
  arXiv  Detail & Related papers  (2020-03-08T13:02:15Z)
• Graphon Pooling in Graph Neural Networks [169.09536309161314]
  Graph neural networks (GNNs) have been used effectively in different applications involving the processing of signals on irregular structures modeled by graphs. We propose a new strategy for pooling and sampling on GNNs using graphons which preserves the spectral properties of the graph.
  arXiv  Detail & Related papers  (2020-03-03T21:04:20Z)

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.