Research map / Optimization / Optimizers
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 FlyingSquid instead of Data Programming | weak-supervision label modeling · Spouse | F1: +4.9 F1 points | Helped |
| Use FlyingSquid instead of Data Programming | weak-supervision label modeling · Spam | F1: +0.5 F1 points | Helped |
| Use FlyingSquid instead of Majority Vote | weak-supervision label modeling · Weather | F1: +1.6 F1 points | Helped |
| Use FlyingSquid instead of Sequential Data Programming | weak-supervision label modeling · Interview | F1: -0.1 F1 points | No clear effect |
| Use FlyingSquid instead of Majority Vote | weak-supervision label modeling · Commercial | F1: +0.5 F1 points | Helped |
| Use FlyingSquid instead of Data Programming | weak-supervision label modeling · Tennis Rally | F1: +0.3 F1 points | No clear effect |
| Use FlyingSquid instead of Sequential Data Programming | weak-supervision label modeling · Basketball | F1: -0.3 F1 points | No clear effect |
| Replace source abstentions with random votes instead of modeling abstentions (ablation) | FlyingSquid · weak-supervision evaluation | F1: -25.6 points | Hurt |
| Use one triplet assignment instead of aggregating across assignments (ablation) | FlyingSquid · weak-supervision evaluation | F1: -23.8 points | Hurt |
| Use FlyingSquid rather than Majority Vote for online labeling | online video weak supervision · Interview streaming | F1: +15.7 F1 points | Helped |
| Use FlyingSquid rather than Majority Vote for online labeling | online video weak supervision · Commercial streaming | F1: +14.1 F1 points | Helped |
| Use FlyingSquid rather than Majority Vote for online labeling | online video weak supervision · Tennis Rally streaming | F1: +1.1 F1 points | Helped |
Closest papers by meaning
- End-to-End Weak Supervision (NeurIPS 2021 · similarity 0.89)
- Weak Supervision Performance Evaluation via Partial Identification (NeurIPS 2024 · similarity 0.88)
- Universalizing Weak Supervision (ICLR 2022 · similarity 0.88)
- A General Framework for Learning from Weak Supervision (ICML 2024 · similarity 0.87)
- Weak-to-Strong Generalization under Distribution Shifts (NeurIPS 2025 · similarity 0.85)
- From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning (NeurIPS 2025 · 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.