mlsanityData to 14 Oct 2026

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

arXiv 2603.07521 ↗First posted 8 Mar 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 8 Mar 2026.

Builds on

27 of 36 references.

References · 27

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  9. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  10. 2025Gemma 3 Technical Reportcited by 1,824
  11. 2020Rethinking Attention with Performerscited by 1,601
  12. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
15 more
  1. 2017Mixed Precision Trainingcited by 1,156
  2. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  3. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
  4. 2017A Neural Representation of Sketch Drawingscited by 313
  5. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  6. 2022cosFormer: Rethinking Softmax in Attentioncited by 213
  7. 2023Exphormer: Sparse Transformers for Graphscited by 170
  8. 2023SGFormer: Simplifying and Empowering Transformers for Large-Graph Representationscited by 133
  9. 2019Wasserstein Weisfeiler-Lehman Graph Kernelscited by 104
  10. 2025Position: Graph Learning Will Lose Relevance Due To Poor Benchmarkscited by 53
  11. 2019Multi-Graph Transformer for Free-Hand Sketch Recognitioncited by 35
  12. 2025Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernelscited by 13
  13. 2025Graph Neural Networks in Modern AI-aided Drug Discoverycited by 12
  14. 2024An end-to-end attention-based approach for learning on graphscited by 11
  15. 2024AnchorGT: Efficient and Flexible Attention Architecture for Scalable Graph Transformerscited by 2

Built on by

Not cited yet.