Research map / Graph learning / Graph algorithms and clustering
Efficient Deep Space Filling Curve
Wanli Chen, Xufeng Yao, Xinyun Zhang, Bei Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-stage MST over ResNet stages 2, 3, 4 (ablation) | EGCN SFC model · MNIST | autocorrelation (k=6): 0.577 (±0.04) -> 0.625 (±0.01) | Improved |
| use siamese self-learning scheme instead of NSFC generator-evaluator (ablation) | SFC model · MNIST | autocorrelation: 0.593 -> 0.625 | Improved |
| use siamese scheme to cut training time per epoch (ablation) | SFC model · MNIST | training time/epoch: 1867s -> 72s | Improved |
| replace GCN with EGCN (no feature normalization) (ablation) | SFC model · MNIST | autocorrelation: 0.594 -> 0.598 | No clear effect |
| add feature normalization layer to EGCN (ablation) | SFC model · MNIST | autocorrelation: 0.598 -> 0.625 | Improved |
| replace GCN by EGCN for grid graphs | graph weight network · 64x64 grid graph, batch 512 | GPU memory / inference time: 104M -> 32M, 11ms -> 4ms | Improved |
| use data-adaptive learned SFC instead of Hilbert | SFC generation · MNIST | LZW code length (bytes): 182.7 -> 158.3 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FastGCN — FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling (ICLR 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Neural Space-Filling Curves (ECCV 2022 · similarity 0.89)
- Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective (ICLR 2022 · similarity 0.84)
- pathGCN: Learning General Graph Spatial Operators from Paths (ICML 2022 · similarity 0.84)
- GSPN-2: Efficient Parallel Sequence Modeling (NeurIPS 2025 · similarity 0.82)
- Spatio-Spectral Graph Neural Networks (NeurIPS 2024 · similarity 0.82)
- Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification (NeurIPS 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
