Research map / Graph learning / Graph self-supervised learning
SHINE: SubHypergraph Inductive Neural nEtwork
Yuan Luo
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 SHINE's subgraph attention and strongly dual attention with pathway information | Disease classification on DisGeNet · DisGeNet test | micro-F1: 0.6809 $\pm$ 0.0027 -> 0.6955 $\pm$ 0.0034 | Improved |
| Use SHINE's subgraph attention and strongly dual attention with pathway information | Cancer classification on TCGA-MC3 · TCGA-MC3 test | micro-F1: 0.5117 $\pm$ 0.0084 -> 0.5319 $\pm$ 0.0049 | Improved |
| Add weighted subgraph attention instead of direct sum aggregation (ablation) | SHINE · DisGeNet test | micro-F1: 0.6472 $\pm$ 0.0053 -> 0.6955 $\pm$ 0.0034 | Improved |
| Add weighted subgraph attention instead of direct sum aggregation (ablation) | SHINE · TCGA-MC3 test | micro-F1: 0.4388 $\pm$ 0.0091 -> 0.5319 $\pm$ 0.0049 | Improved |
| Add hypergraph regularization (ablation) | SHINE · DisGeNet test | micro-F1: 0.6829 $\pm$ 0.0059 -> 0.6955 $\pm$ 0.0034 | Improved |
| Add hypergraph regularization (ablation) | SHINE · TCGA-MC3 test | micro-F1: 0.5247 $\pm$ 0.0048 -> 0.5319 $\pm$ 0.0049 | Improved |
| Use strictly dual attention instead of non-strictly-dual attention (ablation) | SHINE · DisGeNet test | micro-F1: 0.6495 $\pm$ 0.0050 -> 0.6955 $\pm$ 0.0034 | Improved |
| Use strictly dual attention instead of non-strictly-dual attention (ablation) | SHINE · TCGA-MC3 test | micro-F1: 0.4721 $\pm$ 0.0032 -> 0.5319 $\pm$ 0.0049 | Improved |
Later papers that compared with this method
1 later accepted paper reports SHINE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Improved Graph Contrastive Learning for Short Text Classification (AAAI 2024 · better on 7 of 7 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
- GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation (ICLR 2025 · similarity 0.87)
- Improved Expressivity of Hypergraph Neural Networks through High-Dimensional Generalized Weisfeiler-Leman Algorithms (ICML 2025 · similarity 0.85)
- Disentangling Hyperedges through the Lens of Category Theory (NeurIPS 2025 · similarity 0.84)
- Rethinking Cancer Gene Identification Through Graph Anomaly Analysis (AAAI 2025 · similarity 0.84)
- Pre-Training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck (AAAI 2025 · similarity 0.84)
- Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning (ICML 2024 · similarity 0.84)
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.
