arXiv AI
When does Subgroup Balance Matter? Predicting Performance Sensitivity from Latent Separability
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 1
AIA$^{2}$: Attribute-Agnostic Imbalance Augmentation for Subgroup Robustness
arXiv:2608.30297v1 Announce Type: new Abstract: Attributes describing data content and context can induce diverse imbalance patterns that go beyond label imbalance alone. However, existing studies pr...
arXiv Machine Learning
Sep 21
Robust Mixture Models for Algorithmic Fairness Under Latent Heterogeneity
The paper introduces ROME, a framework that learns latent group structure while optimizing worst-group predictive performance. ROME links latent-variable modeling with distributionally robust optimization through an Expectation-Maximization approach for linear models and a neural Mixture-of-Experts for nonlinear settings. Experiments on simulations and three real-world regression datasets show that ROME improves worst-group performance while maintaining competitive overall accuracy compared to existing group-aware and group-label-free robust learning methods.
arXiv AI
Sep 10
Discovering Latent Groups for Robust Classification
arXiv:2606.23609v2 Announce Type: replace-cross Abstract: Machine learning models exploit spurious correlations, achieving high average accuracy but failing disproportionately on underrepresented sub...
arXiv AI
Aug 25
Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization
The paper proposes a fairness-aware Mixture-of-Experts (MoE) framework that tackles routing-induced bias by applying subgroup reweighting to correct data imbalance and gate entropy regularization to prevent the gating network from collapsing onto subgroup attributes. This end-to-end approach keeps expert utilization balanced and interpretable, offering a clear view of how subgroups are allocated across experts. Experiments show that the method improves fairness while maintaining competitive predictive performance.
Hugging Face Trending Papers
Jun 22
Discovering Latent Groups for Robust Classification
Machine learning models exploit spurious correlations, achieving high average accuracy but failing disproportionately on underrepresented subgroups. Existing methods address this by adjusting network parameters, guided either by subgroup annotations or inferred pseudo-group labels.
arXiv Machine Learning
Jun 25
Homogeneity Bias in Open-Weight LLMs Is Robust to Decoding Hyperparameters
arXiv:2501. 02211v2 Announce Type: replace-cross Abstract: Large language models (LLMs) reproduce homogeneity bias -- the tendency to portray marginalized groups as more internally similar than dominant groups -- but whether this bias is stable or an artifact of inference settings has only been studied in single proprietary models.