AI Paper Atlas

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

NeurIPS 2023 · Label-efficient and robust learning › Knowledge distillation · approach: Distillation for machine translation · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
convert REs to BRNN instead of training LSTM/CNN/DAN from scratch (zero-shot)BRNN · Data-center trafficaccuracy (%): 50.4 -> 85.4Improved
BRNN vs CNN with 10% training dataBRNN · Data-center trafficaccuracy (%): 95.5 -> 98.8Improved
BRNN vs CNN with full training dataBRNN · Data-center trafficaccuracy (%): 98.7 -> 99.8Improved
add pooling operation to soft random forest (PSRF vs SRF) (ablation)SRF · Data-center trafficaccuracy (%): 94.7 -> 98.5Improved
pooling in zero-shot (PSRF vs SRF) (ablation)SRF · Data-center trafficaccuracy (%): 79.3 -> 85.1Improved
semi-supervised distillation with soft labels (SRF vs RF) at 1% data (ablation)RF · Data-center trafficaccuracy (%): 78.4 -> 92.9Improved
soft labels instead of hard labels (SRF vs Hard RF) at 1% data (ablation)Hard RF · Data-center trafficaccuracy (%): 86.5 -> 92.9Improved
PSRF replaces RE-based systemRE · Data-center trafficaccuracy (%): 85.4 -> 98.5Improved
pooling window w = 1 (no effective pooling) (ablation)PSRF · Data-center trafficaccuracy (%)Hurt
increase stride s (ablation)PSRF · Data-center trafficaccuracy (%)Hurt
increase window w beyond 2 (ablation)PSRF · Data-center trafficaccuracy (%)No clear effect
increase minimum samples per leaf (ablation)PSRF · Data-center trafficaccuracy (%)Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy