Research map / Label-efficient and robust learning / Recognition and long-tail
DeepPINK: reproducible feature selection in deep neural networks
Yang Lu, Yingying Fan, Jinchi Lv, William Stafford Noble
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 the pairwise-connected layer to make each feature compete with its knockoff (ablation) | MLP with knockoff features · Linear model, p=3000 | Power: 0.43 -> 0.97 | Improved |
| Add the pairwise-connected layer to make each feature compete with its knockoff (ablation) | MLP with knockoff features · Single-Index model, p=3000 | Power: 0.31 -> 1 | Improved |
| Use DeepPINK instead of MLP feature importance (ablation) | Feature selection with knockoffs · Linear model, p=50 | Power: 1 -> 1 | No clear effect |
| Use DeepPINK instead of MLP feature importance (ablation) | Feature selection with knockoffs · Single-Index model, p=50 | Power: 0.89 -> 0.98 | Improved |
| Use DeepPINK instead of DeepLIFT | Feature selection · Linear model, p=3000 | Power: 0.46 -> 0.97 | Improved |
| Use DeepPINK instead of DeepLIFT | Feature selection · Single-Index model, p=3000 | Power: 0.44 -> 1 | Improved |
Closest papers by meaning
- DeepDRK: Deep Dependency Regularized Knockoff for Feature Selection (NeurIPS 2024 · similarity 0.84)
- A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning (NeurIPS 2023 · similarity 0.84)
- Hypernetworks for Dynamic Feature Selection (NeurIPS 2026 · similarity 0.84)
- SAND: One-Shot Feature Selection with Additive Noise Distortion (ICML 2025 · similarity 0.83)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.83)
- Towards Trustworthy Deep Learning (AAAI 2024 · 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.
