SketchGraphNet: A Memory-Efficient Hybrid Graph Transformer for Large-Scale Sketch Corpora Recognition

• URL: http://arxiv.org/abs/2603.07521v1
• Date: Sun, 08 Mar 2026 08:18:57 GMT
• Title: SketchGraphNet: A Memory-Efficient Hybrid Graph Transformer for Large-Scale Sketch Corpora Recognition
• Abstract summary: We propose SketchGraphNet, a hybrid graph neural architecture that integrates local message passing with a memory-efficient global attention mechanism.<n>To support systematic evaluation, we construct SketchGraph, a large-scale benchmark comprising 3.44 million graph-structured sketches across 344 categories.
• Score: 5.072189947670439
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work investigates large-scale sketch recognition from a graph-native perspective, where free-hand sketches are directly modeled as structured graphs rather than raster images or stroke sequences. We propose SketchGraphNet, a hybrid graph neural architecture that integrates local message passing with a memory-efficient global attention mechanism, without relying on auxiliary positional or structural encodings. To support systematic evaluation, we construct SketchGraph, a large-scale benchmark comprising 3.44 million graph-structured sketches across 344 categories, with two variants (A and R) to reflect different noise conditions. Each sketch is represented as a spatiotemporal graph with normalized stroke-order attributes. On SketchGraph-A and SketchGraph-R, SketchGraphNet achieves Top-1 accuracies of 83.62% and 87.61%, respectively, under a unified training configuration. MemEffAttn further reduces peak GPU memory by over 40% and training time by more than 30% compared with Performer-based global attention, while maintaining comparable accuracy.

Related papers

• SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches [54.06877048295693]
  We introduce SketchAgent, a system designed to automate the transformation of hand-drawn sketches into structured diagrams.<n>SketchAgent integrates sketch recognition, symbolic reasoning, and iterative validation to produce semantically coherent and structurally accurate diagrams.<n>By streamlining the diagram generation process, SketchAgent holds great promise for applications in design, education, and engineering.
  arXiv  Detail & Related papers  (2025-08-02T07:22:51Z)
• Plexus: Taming Billion-edge Graphs with 3D Parallel Full-graph GNN Training [5.1420473428862605]
  Graph neural networks (GNNs) leverage the connectivity and structure of real-world graphs to learn intricate properties and relationships between nodes.<n>Many real-world graphs exceed the memory capacity of a GPU due to their sheer size, and training GNNs on such graphs requires techniques such as mini-batch sampling to scale.<n>We propose a three-dimensional (3D) parallel approach for full-graph training that tackles these issues and scales to billion-edge graphs.
  arXiv  Detail & Related papers  (2025-05-07T02:49:52Z)
• Graph Transformers for Large Graphs [57.19338459218758]
  This work advances representation learning on single large-scale graphs with a focus on identifying model characteristics and critical design constraints. A key innovation of this work lies in the creation of a fast neighborhood sampling technique coupled with a local attention mechanism. We report a 3x speedup and 16.8% performance gain on ogbn-products and snap-patents, while we also scale LargeGT on ogbn-100M with a 5.9% performance improvement.
  arXiv  Detail & Related papers  (2023-12-18T11:19:23Z)
• Faster Optimization in S-Graphs Exploiting Hierarchy [8.17925295907622]
  We present an improved version of S-Graphs exploiting the hierarchy to reduce the graph size by marginalizing redundant robot poses. We show similar accuracy compared to the baseline while showing a 39.81% reduction in the computation time with respect to the baseline.
  arXiv  Detail & Related papers  (2023-08-22T07:35:15Z)
• SSR-GNNs: Stroke-based Sketch Representation with Graph Neural Networks [34.759306840182205]
  This paper investigates a graph representation for sketches, where the information of strokes, i.e., parts of a sketch, are encoded on vertices and information of inter-stroke on edges. The resultant graph representation facilitates the training of a Graph Neural Networks for classification tasks. The proposed representation enables generation of novel sketches that are structurally similar to while separable from the existing dataset.
  arXiv  Detail & Related papers  (2022-04-27T19:18:01Z)
• Scaling R-GCN Training with Graph Summarization [71.06855946732296]
  Training of Relation Graph Convolutional Networks (R-GCN) does not scale well with the size of the graph. In this work, we experiment with the use of graph summarization techniques to compress the graph. We obtain reasonable results on the AIFB, MUTAG and AM datasets.
  arXiv  Detail & Related papers  (2022-03-05T00:28:43Z)
• GraphDCA -- a Framework for Node Distribution Comparison in Real and Synthetic Graphs [72.51835626235368]
  We argue that when comparing two graphs, the distribution of node structural features is more informative than global graph statistics. We present GraphDCA - a framework for evaluating similarity between graphs based on the alignment of their respective node representation sets.
  arXiv  Detail & Related papers  (2022-02-08T14:19:19Z)
• Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming [48.99614465020678]
  We introduce a novel self-supervised graph representation learning algorithm via Graph Contrastive Adjusted Zooming. This mechanism enables G-Zoom to explore and extract self-supervision signals from a graph from multiple scales. We have conducted extensive experiments on real-world datasets, and the results demonstrate that our proposed model outperforms state-of-the-art methods consistently.
  arXiv  Detail & Related papers  (2021-11-20T22:45:53Z)
• 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)
• SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks [40.32629073485205]
  We introduce SketchGNN, a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. To predict the per-node labels, our SketchGNN uses graph convolution and a static-dynamic branching network architecture.
  arXiv  Detail & Related papers  (2020-03-02T05:48:55Z)

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.