Group Robust Classification Without Any Group Information
–Neural Information Processing Systems
Firstly, these methods implicitly assume that all group combinations are represented during training. To illustrate this, we introduce a systematic generalization task on the MPI3D dataset and discover that current algorithms fail to improve the ERM baseline when combinations of observed attribute values are missing.
Neural Information Processing Systems
Oct-9-2025, 04:59:16 GMT
- Country:
- Genre:
- Research Report (0.46)
- Industry:
- Education (0.46)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Neural Networks > Deep Learning (0.46)
- Statistical Learning (0.68)
- Natural Language (0.93)
- Representation & Reasoning (1.00)
- Vision (1.00)
- Machine Learning
- Information Technology > Artificial Intelligence