Research map / Label-efficient and robust learning / OOD and anomaly detection
Provably Invariant Learning without Domain Information
Xiaoyu Tan, LIN Yong, Shengyu Zhu, Chao Qu, Xihe Qiu, Xu Yinghui, Peng Cui, Yuan Qi
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 |
|---|---|---|---|
| Feature selection (TIVA-s) instead of feature learning (TIVA-f) on synthetic tabular data | TIVA · Synthetic temporal | Test mean accuracy (%) | Improved |
| Environment-independent TIVA (no domain info) vs. ERM on synthetic temporal data | TIVA-s · Synthetic temporal | Test mean and worst accuracy: ~15% mean and ~40% worst over ERM (averaged) | Improved |
| Feature learning (TIVA-f) with disentanglement on CelebA pretrained ResNet features | TIVA · CelebA | Test worst accuracy (%): 60.32 vs 47.58 for ERM | Improved |
| Feature learning (TIVA-f) on house price data | TIVA · House price | Test mean MSE: 0.305 vs 0.3339 for ZIN | Improved |
| Feature selection (TIVA-s) vs feature learning on Landcover | TIVA · Landcover | OOD test accuracy (%): 68.31 vs 68.26 | No clear effect |
| Feature learning (TIVA-f) on CelebA: lower train accuracy and worse than ERM on mean test accuracy | TIVA · CelebA | Test mean accuracy (%): 72.60 vs 70.76 ERM (ERM higher on train) | Hurt |
| Feature selection (TIVA-s) on CelebA | TIVA · CelebA | Test worst accuracy (%): 45.67 vs 47.58 ERM | Hurt |
| Feature selection on house price (TIVA-s) vs feature learning | TIVA · House price | Test mean MSE: 0.3276 vs 0.3050 | Hurt |
Closest papers by meaning
- ZIN: When and How to Learn Invariance Without Environment Partition? (NeurIPS 2022 · similarity 0.91)
- Environment Inference for Invariant Learning (ICML 2021 · similarity 0.88)
- Sufficient Invariant Learning for Distribution Shift (CVPR 2025 · similarity 0.87)
- Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach (AAAI 2024 · similarity 0.85)
- The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing (NeurIPS 2024 · similarity 0.85)
- Learning Conditional Invariances through Non-Commutativity (ICLR 2024 · similarity 0.84)
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.
