Research map / Label-efficient and robust learning / Recognition and long-tail
A Novel Model for Imbalanced Data Classification
Jian Yin, Chunjing Gan, Kaiqi Zhao, Xuan Lin, Zhe Quan, Zhi-Jie Wang
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 data block construction, data space improvement (LMNN), adaptive weights and weighted ensemble over kNN baselines | DDAE · 14 imbalanced datasets | Recall: cm1 0.688 -> 0.813 vs RP | Improved |
| DDAE versus RP on low-imbalance dataset | DDAE · pc4 | G-mean: 0.873 -> 0.804 | Hurt |
| use adaptive weight adjustment component (ablation) | DDAE · cm1, mw1 | G-mean, F-measure, AUC | Improved |
| use AWA component (ablation) | DDAE · mw1 | Recall | Hurt |
| add data space improvement (LMNN) (ablation) | DDAE · cm1, mw1 | G-mean, F-measure, AUC | Improved |
| add data block construction (with EL and AWA) (ablation) | DDAE · cm1, mw1 | overall metrics | Improved |
| vary cost ratio from 2 to imbalance ratio (ablation) | DDAE · cm1, mw1 | all metrics | No clear effect |
| increase gamma above 0.2 (ablation) | DDAE · cm1 | recall, G-mean, F, AUC: drop by 0.25, 0.077, 0.085, 0.062 | Hurt |
| set number of blocks close to imbalance ratio rather than small (ablation) | DDAE · cm1, mw1 | all metrics | Improved |
Closest papers by meaning
- Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data (ICML 2025 · similarity 0.86)
- Learning Imbalanced Data with Beneficial Label Noise (ICML 2025 · similarity 0.85)
- Restoring balance: principled under/oversampling of data for optimal classification (ICML 2024 · similarity 0.83)
- Concentration and excess risk bounds for imbalanced classification with synthetic oversampling (NeurIPS 2025 · similarity 0.83)
- Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance (ICML 2024 · similarity 0.83)
- Learning under Localized Minority Imbalance (NeurIPS 2026 · 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.
