Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Learning on Data Streams via Temporal Label Propagation
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 |
|---|---|---|---|
| Add star-mesh short-circuit history summarization (TLP vs SWLP) (ablation) | sliding-window label propagation · Incart-ECG | accuracy (%): 69.6 -> 94.9 | Helped |
| Add short-circuit summarization (TLP vs SWLP) (ablation) | sliding-window label propagation · Daphnet-Gait | accuracy (%): 56.3 -> 75.9 | Helped |
| Add short-circuit summarization (TLP vs SWLP) (ablation) | sliding-window label propagation · CamVid-Car | accuracy (%): 80.6 -> 95.9 | Helped |
| Add short-circuit summarization (TLP vs SWLP) on stream without temporal order (ablation) | sliding-window label propagation · Caltech10-101 | accuracy (%): 78.1 -> 80.9 | No clear effect |
| Short-circuiting versus window only (ablation) | TLP vs SWLP · Incart-ECG | avg time per point (msec): 0.051 -> 0.052 | No clear effect |
| Replace k-center quantization (QLP) with TLP | QLP · Daphnet-Gait | avg time per point (msec): 104.3 -> 15.8 | Helped |
| Use TLP instead of inductive LP (non-updating model) | ILP · CamVid-Car | accuracy (%): 86.9 -> 95.9 | Helped |
| Use TLP instead of quantized LP | QLP · CamVid-Car | accuracy (%): 54.5 -> 95.9 | Helped |
| Use only two labeled examples per class | TLP · Incart-ECG | accuracy (%): 94.9 | Helped |
Closest papers by meaning
- Semi-Supervised Streaming Learning with Emerging New Labels (AAAI 2020 · similarity 0.90)
- Data driven semi-supervised learning (NeurIPS 2021 · similarity 0.86)
- Learning with Partial-Label and Unlabeled Data: A Uniform Treatment for Supervision Redundancy and Insufficiency (ICML 2024 · similarity 0.84)
- Fast Co-Training under Weak Dependence via Stream-Based Active Learning (ICML 2024 · similarity 0.84)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.83)
- InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning (ICML 2024 · similarity 0.83)
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.