ViG-LRGC: Vision Graph Neural Networks with Learnable Reparameterized Graph Construction

• URL: http://arxiv.org/abs/2509.18840v1
• Date: Tue, 23 Sep 2025 09:25:22 GMT
• Title: ViG-LRGC: Vision Graph Neural Networks with Learnable Reparameterized Graph Construction
• Authors: Ismael Elsharkawi, Hossam Sharara, Ahmed Rafea,
• Abstract summary: 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.
• Score: 0.15293427903448023
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image Representation Learning is an important problem in Computer Vision. Traditionally, images were processed as grids, using Convolutional Neural Networks or as a sequence of visual tokens, using Vision Transformers. Recently, Vision Graph Neural Networks (ViG) have proposed the treatment of images as a graph of nodes; which provides a more intuitive image representation. The challenge is to construct a graph of nodes in each layer that best represents the relations between nodes and does not need a hyper-parameter search. ViG models in the literature depend on non-parameterized and non-learnable statistical methods that operate on the latent features of nodes to create a graph. This might not select the best neighborhood for each node. Starting from k-NN graph construction to HyperGraph Construction and Similarity-Thresholded graph construction, these methods lack the ability to provide a learnable hyper-parameter-free graph construction method. To overcome those challenges, we present the Learnable Reparameterized Graph Construction (LRGC) for Vision Graph Neural Networks. LRGC applies key-query attention between every pair of nodes; then uses soft-threshold reparameterization for edge selection, which allows the use of a differentiable mathematical model for training. Using learnable parameters to select the neighborhood removes the bias that is induced by any clustering or thresholding methods previously introduced in the literature. In addition, LRGC allows tuning the threshold in each layer to the training data since the thresholds are learnable through training and are not provided as hyper-parameters to the model. We demonstrate that the proposed ViG-LRGC approach outperforms state-of-the-art ViG models of similar sizes on the ImageNet-1k benchmark dataset.

Related papers

• Vision Graph Prompting via Semantic Low-Rank Decomposition [10.223578525761617]
  Vision GNN (ViG) demonstrates superior performance by representing images as graph structures.<n>To efficiently adapt ViG to downstream tasks, parameter-efficient fine-tuning techniques like visual prompting become increasingly essential.<n>We propose Vision Graph Prompting (VGP), a novel framework tailored for vision graph structures.
  arXiv  Detail & Related papers  (2025-05-07T04:29:29Z)
• ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning [7.325055402812975]
  Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have dominated the field of Computer Vision (CV)<n>Recent works addressing this bottleneck impose constraints on the flexibility of GNNs to build unstructured graphs.<n>We propose a novel method called Dynamic Efficient Graph Convolution (DEGC) for designing efficient and globally aware ViGs.
  arXiv  Detail & Related papers  (2025-01-18T02:59:10Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs)<n>This framework provides a standardized setting to evaluate GNNs across diverse datasets.<n>We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network [7.556253645434246]
  We introduce an innovative adaptive graph construction method that utilizes a filtering mechanism based on distance and dynamic threshold similarity.<n>We also combine the global awareness capabilities of Transformers to enhance the model's representation of graph structures.<n>Our system achieves an average improvement of 3.8x-40.3x in overall matching performance.
  arXiv  Detail & Related papers  (2024-12-24T07:05:55Z)
• Training Graph Neural Networks on Growing Stochastic Graphs [114.75710379125412]
  Graph Neural Networks (GNNs) rely on graph convolutions to exploit meaningful patterns in networked data. We propose to learn GNNs on very large graphs by leveraging the limit object of a sequence of growing graphs, the graphon.
  arXiv  Detail & Related papers  (2022-10-27T16:00:45Z)
• Vision GNN: An Image is Worth Graph of Nodes [49.3335689216822]
  We propose to represent the image as a graph structure and introduce a new Vision GNN (ViG) architecture to extract graph-level feature for visual tasks. Based on the graph representation of images, we build our ViG model to transform and exchange information among all the nodes. Extensive experiments on image recognition and object detection tasks demonstrate the superiority of our ViG architecture.
  arXiv  Detail & Related papers  (2022-06-01T07:01:04Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)
• 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)
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings [53.58077686470096]
  We propose an end-to-end graph learning framework, namely Iterative Deep Graph Learning (IDGL) for jointly and iteratively learning graph structure and graph embedding. Our experiments show that our proposed IDGL models can consistently outperform or match the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-06-21T19:49:15Z)
• Optimal Transport Graph Neural Networks [31.191844909335963]
  Current graph neural network (GNN) architectures naively average or sum node embeddings into an aggregated graph representation. We introduce OT-GNN, a model that computes graph embeddings using parametric prototypes.
  arXiv  Detail & Related papers  (2020-06-08T14:57:39Z)
• Graph Representation Learning Network via Adaptive Sampling [4.996520403438455]
  Graph Attention Network (GAT) and GraphSAGE are neural network architectures that operate on graph-structured data. One challenge raised by GraphSAGE is how to smartly combine neighbour features based on graph structure. We propose a new architecture to address these issues that is more efficient and is capable of incorporating different edge type information.
  arXiv  Detail & Related papers  (2020-06-08T14:36:20Z)

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.