Research map / Label-efficient and robust learning / OOD and anomaly detection
Benchmarking Distribution Shift in Tabular Data with TableShift
Josh Gardner, Zoran Popovic, Ludwig Schmidt
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 |
|---|---|---|---|
| Increase in-distribution accuracy across models and tasks | Tabular classifiers evaluated on TableShift · 15 TableShift tasks | out-of-distribution accuracy: ρ=0.81 | Improved |
| Apply domain robustness or domain generalization methods instead of standard baselines | Tasks with multiple training subdomains · TableShift domain generalization tasks | in-distribution accuracy | Hurt |
| Apply domain robustness or domain generalization methods instead of standard baselines | Tasks with multiple training subdomains · TableShift domain generalization tasks | shift gap | Mixed |
| Use label-shift robustness methods | Tabular classifiers evaluated on TableShift · TableShift tasks | shift gap | No clear effect |
| Use label-shift robustness methods | Tabular classifiers evaluated on TableShift · TableShift tasks | ID and OOD accuracy | Hurt |
| Increase change in label distribution | Models evaluated across TableShift tasks · TableShift tasks | absolute shift gap: ρ = 0.71 | Mixed |
| Use tabular methods beyond standard tree-based baselines | Tabular classifiers evaluated on TableShift · 15 TableShift tasks | OOD accuracy | No clear effect |
Closest papers by meaning
- TabFSBench: Tabular Benchmark for Feature Shifts in Open Environments (ICML 2025 · similarity 0.93)
- TabArena: A Living Benchmark for Machine Learning on Tabular Data (NeurIPS 2025 · similarity 0.88)
- A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data (NeurIPS 2024 · similarity 0.87)
- TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks (ICLR 2025 · similarity 0.87)
- TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation (ICLR 2025 · similarity 0.87)
- Fully Test-time Adaptation for Tabular Data (AAAI 2025 · similarity 0.87)
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.
