Research map / Label-efficient and robust learning / Recognition and long-tail
Consistent feature selection for analytic deep neural networks
Vu C Dinh, Lam S Ho
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 adaptive group lasso step after group lasso (GL+AGL vs GL) (ablation) | Group Lasso feature selection · Synthetic 3x20 network, 100 datasets | runs selecting correct support: 63 out of 100 runs | Improved |
| add adaptive group lasso step after group lasso (ablation) | Group Lasso feature selection · Boston housing | predictors selected: 13 -> 11 | Improved |
| add 13 random Gaussian noise predictors, compare GL vs GL+AGL | Boston housing feature selection · Boston housing + 13 noise predictors, 100 datasets | selection frequency of noise predictors | Improved |
Closest papers by meaning
- A Benchmark for Interpretability Methods in Deep Neural Networks (NeurIPS 2019 · similarity 0.84)
- DeepPINK: reproducible feature selection in deep neural networks (NeurIPS 2018 · similarity 0.83)
- Local Feature Selection without Label or Feature Leakage for Interpretable Machine Learning Predictions (ICML 2024 · similarity 0.82)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.81)
- Active feature acquisition via explainability-driven ranking (ICML 2025 · similarity 0.80)
- Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness (ICLR 2025 · similarity 0.80)
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.
