Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction: A Multi-Dataset Study
Rushuang Zhou, Lei Lü, Zijun Liu, Ting Xiang, Zhen Liang, David Andrew Clifton, Yining Dong, Yuan‐Ting Zhang
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 pseudo-label generation (ablation) | ECGMatch · Chapman (within-dataset) | MAP: 0.761±0.010 -> 0.775±0.014 | Improved |
| add pseudo-label generation (ablation) | ECGMatch · Chapman (within-dataset) | Hamming loss: 0.163±0.009 -> 0.139±0.002 | Improved |
| add pseudo-label refinement (ablation) | ECGMatch · Chapman (cross-dataset) | Hamming loss: 0.242±0.007 -> 0.219±0.003 | Improved |
| add pseudo-label refinement (ablation) | ECGMatch · Chapman (cross-dataset) | MAP: 0.732±0.006 -> 0.748±0.004 | Mixed |
| add label correlation alignment (ablation) | ECGMatch · Mix-dataset | Hamming loss: 0.282±0.010 -> 0.270±0.001 | Improved |
| add label correlation alignment (ablation) | ECGMatch · Mix-dataset | MAP: 0.640±0.010 -> 0.658±0.006 | Improved |
| add pseudo-label refinement (ablation) | ECGMatch · Ningbo (within-dataset) | MAP: 0.805±0.004 vs 0.808±0.001 | No clear effect |
| add ECGMatch's neighbor agreement refinement versus threshold methods | ECGMatch · Cross-dataset protocol | MAP: 0.632±0.005 -> 0.657±0.009 (G12EC, FlexMatch) | Improved |
| add label correlation modeling versus PercentMatch and UPS | ECGMatch · PTB-XL (cross-dataset) | MAP: 0.558±0.004 -> 0.591±0.012 | Improved |
| use ECGAugment instead of fixed sequential perturbations (ablation) | ECGMatch · Four datasets, three protocols | all metrics | Improved |
| vary lambda_u and lambda_f from 0 to 1.6 (ablation) | ECGMatch · Sensitivity analysis | all metrics | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- SoftMatch — SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning (ICLR 2023) · better on 1 of 1 shared result
- FlexMatch — FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling (NeurIPS 2021) · better on 1 of 1 shared result
- FixMatch — FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (NeurIPS 2020) · better on 1 of 1 shared result
- MixMatch — MixMatch: A Holistic Approach to Semi-Supervised Learning (NeurIPS 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- H-Tuning: Toward Low-Cost and Efficient ECG-based Cardiovascular Disease Detection with Pre-Trained Models (ICML 2025 · similarity 0.86)
- From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining (ICML 2025 · similarity 0.85)
- Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners (ICML 2025 · similarity 0.83)
- Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement (ICML 2024 · similarity 0.83)
- GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images (NeurIPS 2025 · similarity 0.83)
- Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model (ICLR 2025 · 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.
