Research map / Label-efficient and robust learning / Knowledge distillation
Metis: Understanding and Enhancing In-Network Regular Expressions
Zhengxin Zhang, Yucheng Huang, Guanglin Duan, Qing Li, Dan Zhao, Yong Jiang, Lianbo Ma, Xi Xiao, Hengyang Xu
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 |
|---|---|---|---|
| convert REs to BRNN instead of training LSTM/CNN/DAN from scratch (zero-shot) | BRNN · Data-center traffic | accuracy (%): 50.4 -> 85.4 | Improved |
| BRNN vs CNN with 10% training data | BRNN · Data-center traffic | accuracy (%): 95.5 -> 98.8 | Improved |
| BRNN vs CNN with full training data | BRNN · Data-center traffic | accuracy (%): 98.7 -> 99.8 | Improved |
| add pooling operation to soft random forest (PSRF vs SRF) (ablation) | SRF · Data-center traffic | accuracy (%): 94.7 -> 98.5 | Improved |
| pooling in zero-shot (PSRF vs SRF) (ablation) | SRF · Data-center traffic | accuracy (%): 79.3 -> 85.1 | Improved |
| semi-supervised distillation with soft labels (SRF vs RF) at 1% data (ablation) | RF · Data-center traffic | accuracy (%): 78.4 -> 92.9 | Improved |
| soft labels instead of hard labels (SRF vs Hard RF) at 1% data (ablation) | Hard RF · Data-center traffic | accuracy (%): 86.5 -> 92.9 | Improved |
| PSRF replaces RE-based system | RE · Data-center traffic | accuracy (%): 85.4 -> 98.5 | Improved |
| pooling window w = 1 (no effective pooling) (ablation) | PSRF · Data-center traffic | accuracy (%) | Hurt |
| increase stride s (ablation) | PSRF · Data-center traffic | accuracy (%) | Hurt |
| increase window w beyond 2 (ablation) | PSRF · Data-center traffic | accuracy (%) | No clear effect |
| increase minimum samples per leaf (ablation) | PSRF · Data-center traffic | accuracy (%) | Hurt |
Closest papers by meaning
- R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing (NeurIPS 2025 · similarity 0.81)
- Training Neural Networks as Recognizers of Formal Languages (ICLR 2025 · similarity 0.81)
- Self-Supervised Learning of Graph Representations for Network Intrusion Detection (NeurIPS 2025 · similarity 0.81)
- CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition (ICML 2025 · similarity 0.81)
- DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model (NeurIPS 2024 · similarity 0.81)
- Locality-Aware Graph Rewiring in GNNs (ICLR 2024 · similarity 0.81)
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.
