Research map / Graph learning / GNN architectures
You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use learned Set Transformer multiset functions in AllSet | AllSetTransformer · Yelp | accuracy (%): 36.89 ± 0.51 vs 33.04 ± 0.62 | Helped |
| Use learned Set Transformer multiset functions in AllSet | AllSetTransformer · Walmart(1) | accuracy (%): 65.46 ± 0.25 vs 62.00 ± 0.24 | Helped |
| Use learned Set Transformer multiset functions in AllSet | AllSetTransformer · Zoo | accuracy (%): 97.50 ± 3.59 vs 93.65 ± 6.15 | Helped |
| Use learned Set Transformer multiset functions in AllSet | AllSetTransformer · Cora | accuracy (%): 78.59 ± 1.47 vs 80.18 ± 1.15 | Hurt |
| Use learned Set Transformer multiset functions in AllSet | AllSetTransformer · Citeseer | accuracy (%): 73.08 ± 1.20 vs 74.12 ± 1.52 | Hurt |
| Use learned Set Transformer multiset functions in AllSet | AllSetTransformer · Pubmed | accuracy (%): 88.72 ± 0.37 vs 88.75 ± 0.33 | No clear effect |
| Use Deep Sets instead of Set Transformer (ablation) | AllSet · Yelp | accuracy (%): 36.89 ± 0.51 -> 30.36 ± 1.57 | Hurt |
| Use Deep Sets instead of Set Transformer (ablation) | AllSet · Zoo | accuracy (%): 97.50 ± 3.59 -> 95.39 ± 4.77 | Hurt |
| Use Deep Sets instead of Set Transformer (ablation) | AllSet · Pubmed | accuracy (%): 88.72 ± 0.37 -> 88.75 ± 0.33 | No clear effect |
| Use Deep Sets instead of Set Transformer (ablation) | AllSet · Walmart(0.6) | accuracy (%): 78.46 ± 0.40 -> 78.46 ± 0.26 | No clear effect |
| Replace hypergraph propagation with clique expansion plus GCN | AllSetTransformer · Yelp | accuracy (%) | Mixed |
| Use attention-based learned multiset functions rather than unweighted sum aggregation | AllSetTransformer · hypergraph node classification | accuracy | Helped |
Closest papers by meaning
- Training-Free Message Passing for Learning on Hypergraphs (ICLR 2025 · similarity 0.91)
- When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline (AAAI 2025 · similarity 0.90)
- Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification (NeurIPS 2025 · similarity 0.90)
- Hypergraph Neural Architecture Search (AAAI 2024 · similarity 0.89)
- SPHINX: Structural Prediction using Hypergraph Inference Network (ICML 2025 · similarity 0.89)
- K-hop Hypergraph Neural Network: A Comprehensive Aggregation Approach (AAAI 2025 · similarity 0.89)
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.