Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs

• URL: http://arxiv.org/abs/2510.13740v1
• Date: Wed, 15 Oct 2025 16:47:09 GMT
• Title: Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs
• Authors: Mustafa Munir, Alex Zhang, Radu Marculescu,
• Abstract summary: Vision graph neural networks (ViG) have demonstrated promise in vision tasks as a competitive alternative to conventional convolutional neural nets (CNN) and transformers (ViTs)<n>We propose a new graph construction method, Logarithmic Scalable Graph Construction (LSGC) to enhance performance by limiting the number of long-range links.<n>Our smallest model, Ti-LogViG, achieves an average top-1 accuracy on ImageNet-1K of 71.7% with a standard deviation of 0.2%.
• Score: 25.60289758013904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision graph neural networks (ViG) have demonstrated promise in vision tasks as a competitive alternative to conventional convolutional neural nets (CNN) and transformers (ViTs); however, common graph construction methods, such as k-nearest neighbor (KNN), can be expensive on larger images. While methods such as Sparse Vision Graph Attention (SVGA) have shown promise, SVGA's fixed step scale can lead to over-squashing and missing multiple connections to gain the same information that could be gained from a long-range link. Through this observation, we propose a new graph construction method, Logarithmic Scalable Graph Construction (LSGC) to enhance performance by limiting the number of long-range links. To this end, we propose LogViG, a novel hybrid CNN-GNN model that utilizes LSGC. Furthermore, inspired by the successes of multi-scale and high-resolution architectures, we introduce and apply a high-resolution branch and fuse features between our high-resolution and low-resolution branches for a multi-scale high-resolution Vision GNN network. Extensive experiments show that LogViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification and semantic segmentation tasks. Our smallest model, Ti-LogViG, achieves an average top-1 accuracy on ImageNet-1K of 79.9% with a standard deviation of 0.2%, 1.7% higher average accuracy than Vision GNN with a 24.3% reduction in parameters and 35.3% reduction in GMACs. Our work shows that leveraging long-range links in graph construction for ViGs through our proposed LSGC can exceed the performance of current state-of-the-art ViGs. Code is available at https://github.com/mmunir127/LogViG-Official.

Related papers

• DVHGNN: Multi-Scale Dilated Vision HGNN for Efficient Vision Recognition [7.762533819978473]
  We propose a novel vision architecture, termed Dilated Vision HyperGraph Neural Network (DVHGNN)<n>DVHGNN is designed to leverage multi-scale hypergraph to efficiently capture high-order correlations among objects.<n>Our DVHGNN-S achieves an impressive top-1 accuracy of 83.1% on ImageNet-1K, surpassing ViG-S by +1.0% and ViHGNN-S by +0.6%.
  arXiv  Detail & Related papers  (2025-03-19T03:45:23Z)
• 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)
• GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs [5.895049552752008]
  Vision graph neural networks (ViG) offer a new avenue for exploration in computer vision. A major bottleneck in ViGs is the inefficient k-nearest neighbor (KNN) operation used for graph construction. We propose a new method for designing ViGs, Dynamic Axial Graph Construction (DAGC), which is more efficient than KNN. We also propose a novel CNN-GNN architecture, GreedyViG, which uses DAGC.
  arXiv  Detail & Related papers  (2024-05-10T23:21:16Z)
• T-GAE: Transferable Graph Autoencoder for Network Alignment [79.89704126746204]
  T-GAE is a graph autoencoder framework that leverages transferability and stability of GNNs to achieve efficient network alignment without retraining. Our experiments demonstrate that T-GAE outperforms the state-of-the-art optimization method and the best GNN approach by up to 38.7% and 50.8%, respectively.
  arXiv  Detail & Related papers  (2023-10-05T02:58:29Z)
• PVG: Progressive Vision Graph for Vision Recognition [48.11440886492801]
  We propose a Progressive Vision Graph (PVG) architecture for vision recognition task.<n>PVG contains three main components: 1) Progressively Separated Graph Construction (PSGC), 2) Neighbor nodes information aggregation and update module, and 3) Graph error Linear Unit (GraphLU)
  arXiv  Detail & Related papers  (2023-08-01T14:35:29Z)
• MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment [8.29394286023338]
  We propose a novel unified design-mapping approach for efficient processing of vision GNN workloads on heterogeneous MPSoC platforms. MaGNAS employs a two-tier evolutionary search to identify optimal GNNs and mapping pairings that yield the best performance trade-offs. Our experimental results demonstrate that MaGNAS is able to provide 1.57x latency speedup and is 3.38x more energy-efficient for several vision datasets executed on the Xavier MPSoC vs. the GPU-only deployment.
  arXiv  Detail & Related papers  (2023-07-16T14:56:50Z)
• Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication [100.51884192970499]
  GNNs are a powerful family of neural networks for learning over graphs. scaling GNNs either by deepening or widening suffers from prevalent issues of unhealthy gradients, over-smoothening, information squashing. We propose not to deepen or widen current GNNs, but instead present a data-centric perspective of model soups tailored for GNNs.
  arXiv  Detail & Related papers  (2023-06-18T03:33:46Z)
• LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation [51.552170474958736]
  We propose to capture long-distance dependency in graphs by shallower models instead of deeper models, which leads to a much more efficient model, LazyGNN, for graph representation learning. LazyGNN is compatible with existing scalable approaches (such as sampling methods) for further accelerations through the development of mini-batch LazyGNN. Comprehensive experiments demonstrate its superior prediction performance and scalability on large-scale benchmarks.
  arXiv  Detail & Related papers  (2023-02-03T02:33:07Z)
• A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking [124.21408098724551]
  Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs) We present a new ensembling training manner, named EnGCN, to address the existing issues. Our proposed method has achieved new state-of-the-art (SOTA) performance on large-scale datasets.
  arXiv  Detail & Related papers  (2022-10-14T03:43:05Z)
• A Unified Lottery Ticket Hypothesis for Graph Neural Networks [82.31087406264437]
  We present a unified GNN sparsification (UGS) framework that simultaneously prunes the graph adjacency matrix and the model weights. We further generalize the popular lottery ticket hypothesis to GNNs for the first time, by defining a graph lottery ticket (GLT) as a pair of core sub-dataset and sparse sub-network.
  arXiv  Detail & Related papers  (2021-02-12T21:52:43Z)
• Graph Highway Networks [77.38665506495553]
  Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency. They suffer from the notorious over-smoothing problem, in which the learned representations converge to alike vectors when many layers are stacked. We propose Graph Highway Networks (GHNet) which utilize gating units to balance the trade-off between homogeneity and heterogeneity in the GCN learning process.
  arXiv  Detail & Related papers  (2020-04-09T16:26:43Z)

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.