Research map / Graph learning / GNN architectures
Anchor-guided Hypergraph Condensation with Dual-level Discrimination
Fan Li, Xiaoyang Wang, Chen Chen, Wenjie Zhang
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 L_c (coarse-grained loss) (ablation) | AHGCDD · Cora (r=1%) | accuracy (%): 72.67 -> 76.48 | Improved |
| add L_f (fine-grained loss) (ablation) | AHGCDD · Cora (r=1%) | accuracy (%): 74.15 -> 76.48 | Improved |
| add dynamic weighting instead of static (ablation) | AHGCDD · Cora (r=1%) | accuracy (%): 75.63 -> 76.48 | Improved |
| add L_c (ablation) | AHGCDD · DBLP-CA (r=0.5%) | accuracy (%): 87.40 -> 88.80 | Improved |
| add L_f (ablation) | AHGCDD · DBLP-CA (r=0.5%) | accuracy (%): 86.93 -> 88.80 | Improved |
| add dynamic weighting (ablation) | AHGCDD · DBLP-CA (r=0.5%) | accuracy (%): 87.79 -> 88.80 | Improved |
| add L_c (ablation) | AHGCDD · MAG-PM (r=0.25%) | accuracy (%): 56.19 -> 57.55 | Improved |
| add L_f (ablation) | AHGCDD · MAG-PM (r=0.25%) | accuracy (%): 55.97 -> 57.55 | Improved |
| add dynamic weighting (ablation) | AHGCDD · MAG-PM (r=0.25%) | accuracy (%): 56.84 -> 57.55 | Improved |
| use HKPR instead of vanilla hypergraph message passing for node initialization (ablation) | AHGCDD · Cora, DBLP-CA, MAG-PM | accuracy | Improved |
| keep structural information propagation in initialization (ablation) | AHGCDD · Cora, DBLP-CA, MAG-PM | accuracy | Improved |
| use anchor-adaptive threshold instead of shared learnable threshold (ablation) | AHGCDD · Cora, DBLP-CA, MAG-PM | accuracy | Improved |
Closest papers by meaning
- Training-Free Message Passing for Learning on Hypergraphs (ICLR 2025 · similarity 0.89)
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (AAAI 2025 · similarity 0.89)
- Hypergraph Neural Architecture Search (AAAI 2024 · similarity 0.88)
- LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100x Faster Inference (ICLR 2024 · similarity 0.88)
- Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms (ICML 2025 · similarity 0.88)
- Deep Hypergraph Neural Networks with Tight Framelets (AAAI 2025 · similarity 0.88)
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.
