Research map / Graph learning / Knowledge and temporal graphs
Exploring Motif-based Heterogeneous Graph Learning for ReDoS Detection
Hong Huang, Chengyu Yao, Rongchen Li, Weihao Su, Chengyao Peng, Haiming Chen, Guiyi He
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 kernel alignment (ablation) | RMGNN · Corpus (Python) | F1: 66.69 -> 77.73 | Improved |
| add kernel alignment (ablation) | RMGNN · PyPI (Python) | F1: 57.17 -> 67.02 | Improved |
| add kernel alignment (ablation) | RMGNN · Maven (Java) | F1: 48.86 -> 64.41 | Improved |
| add kernel alignment (ablation) | RMGNN · NuGet (.NET) | F1: 53.22 -> 59.88 | Improved |
| add cross-attention fusion instead of mean pooling (ablation) | RMGNN · Corpus (Python) | F1: 70.80 -> 77.73 | Improved |
| add cross-attention fusion instead of mean pooling (ablation) | RMGNN · Maven (Java) | F1: 49.60 -> 64.41 | Improved |
| add cross-attention fusion instead of mean pooling (ablation) | RMGNN · PyPI (Python) | F1: 54.92 -> 67.02 | Improved |
| add cross-attention fusion instead of mean pooling (ablation) | RMGNN · NuGet (.NET) | F1: 53.88 -> 59.88 | Improved |
| replace AST with motif-enhanced HRG input (ablation) | RMGNN · Corpus (Python) | F1: 60.54 -> 77.73 | Improved |
| replace AST with motif-enhanced HRG input (ablation) | RMGNN · Maven (Java) | F1: 28.87 -> 64.41 | Improved |
| add motif enhancement to HRG (ablation) | RMGNN · Corpus (Python) | F1: 65.04 -> 77.73 | Improved |
| use RMGNN GNN design instead of GCN on same HRG (ablation) | RMGNN · all four datasets | F1: 5.9% average F1 gain | Improved |
Closest papers by meaning
- A Label-free Heterophily-guided Approach for Unsupervised Graph Fraud Detection (AAAI 2025 · similarity 0.83)
- Clean-Label Graph Backdoor Attack in the Node Classification Task (AAAI 2025 · similarity 0.82)
- Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification (NeurIPS 2025 · similarity 0.82)
- Redundancy-Aware Test-Time Graph Out-of-Distribution Detection (NeurIPS 2025 · similarity 0.82)
- Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations (CVPR 2025 · similarity 0.82)
- Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors (NeurIPS 2026 · similarity 0.82)
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.
