Research map / Graph learning / GNN architectures
Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs
Naganand Yadati
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 |
|---|---|---|---|
| use MPNN-R on depth 0 and 1 hyperedges instead of MAGNN | MPNN-R · arXiv | test error (%): 24.23 -> 22.34 | Improved |
| use MPNN-R instead of HetGNN | MPNN-R · ACM | test error (%): 23.43 -> 20.32 | Improved |
| use MPNN-R instead of MAGNN | MPNN-R · DBLP | test error (%): 21.68 -> 21.45 | No clear effect |
| use depth 0 and 1 hyperedges (HetGNN) instead of depth 0 only (HGNN) | HGNN · Cora | test error (%): 32.41 -> 27.45 | Improved |
| use graph structure (HGNN) instead of MLP ignoring it | MLP · Cora | test error (%): 42.14 -> 32.41 | Improved |
| use G-MPNN with relation and position info instead of HGNN | HGNN · WP-IND | MRR: 0.072 -> 0.200 | Improved |
| use G-MPNN-max instead of HGNN | HGNN · MFB-IND | MRR: 0.121 -> 0.268 | Improved |
| choice of aggregator g: sum vs mean vs max | G-MPNN · JF-IND | MRR: sum 0.219, mean 0.112, max 0.216 | Mixed |
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.
- HyperGCN — HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs (NeurIPS 2019) · better on 3 of 3 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
- Training-Free Message Passing for Learning on Hypergraphs (ICLR 2025 · similarity 0.89)
- Probabilistically Rewired Message-Passing Neural Networks (ICLR 2024 · similarity 0.87)
- Probabilistic Graph Rewiring via Virtual Nodes (NeurIPS 2024 · similarity 0.87)
- Improving the Effective Receptive Field of Message-Passing Neural Networks (ICML 2025 · similarity 0.86)
- Towards Dynamic Message Passing on Graphs (NeurIPS 2024 · similarity 0.85)
- ENAHPool: The Edge-Node Attention-based Hierarchical Pooling for Graph Neural Networks (ICML 2025 · similarity 0.85)
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.
