Research map / Architectures and efficiency / RNNs and normalization
HONet: Data-Efficient Learning for Exact Cover Tasks via Hypergraph Optimization
Pengyang Huang, Zirui Zhuang, Haifeng Sun, Qi Qi, Jingyu Wang, Jianxin Liao
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 relaxation gap loss Lgap (GCL) (ablation) | HONet · Sudoku 9x9 (20-22 Givens) | whole-board accuracy (%): 99.70 -> 100.00 | Improved |
| add relaxation gap loss Lgap (GCL) (ablation) | HONet · Sudoku 9x9 (26-28 Givens) | relaxation gap: ~10-2 -> ~10-5 | Improved |
| add relaxation gap loss Lgap (GCL) (ablation) | HONet · Sudoku 9x9 (26-28 Givens) | inference time: 56.51ms -> 11.45ms | Improved |
| use hypergraph encoder instead of Graph Transformer (ablation) | HONet · Sudoku 9x9 (26-28 Givens) | epochs to peak validation: 18 -> 4 | Improved |
| use hypergraph encoder instead of Graph Transformer (ablation) | HONet · Sudoku 9x9 (20-22 Givens) | whole-board accuracy (%): 99.50 -> 100.00 | Improved |
| add neural network objective shaping instead of direct projection of clues (ablation) | HONet · Sudoku 9x9 (20-22 Givens) | whole-board accuracy (%): 30.20 -> 100.00 | Improved |
| add auxiliary warm-start loss Lwarm and reduce lambda (ablation) | HONet · Sudoku 9x9 (17-19 Givens) | whole-board accuracy (%): ~3 -> 91.80 | Improved |
| train on 20-22 Givens only, test zero-shot on 17-19 Givens | HONet · Sudoku 9x9 (OOD) | whole-board accuracy (%): 87.50 | Improved |
| reduce training set to 500 samples (~5%) (ablation) | HONet · Sudoku 9x9 (Medium/Hard) | whole-board accuracy (%): > 99 | No clear effect |
| reduce training set to 100 samples (~1%) (ablation) | HONet · Sudoku 9x9 (Medium/Hard) | whole-board accuracy (%): ~90 | Hurt |
| replace SATNet solver layer with HONet | Visual Sudoku model · Visual Sudoku | test accuracy (%): 63.20 -> 98.40 | Improved |
| replace SATNet with HONet | Visual Sudoku model · Visual Sudoku | epochs to peak: 99 -> 24 | 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.
- SATNet (9k) — SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver (ICML 2019) · better on 5 of 5 shared results
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
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (AAAI 2025 · similarity 0.85)
- LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100x Faster Inference (ICLR 2024 · similarity 0.84)
- Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error (NeurIPS 2025 · similarity 0.84)
- Deep Hypergraph Neural Networks with Tight Framelets (AAAI 2025 · similarity 0.84)
- SPHINX: Structural Prediction using Hypergraph Inference Network (ICML 2025 · similarity 0.83)
- Are Graph Neural Networks Optimal Approximation Algorithms? (NeurIPS 2024 · similarity 0.83)
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.
