arXiv Machine Learning September 2, 2026 By Yiming Luo, Rongqiang Zhao, Jie Liu

SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations

Read the original on arXiv Machine Learning →

SAGE (Subpopulation-Aware Generative Enhancement) is a two-stage generative augmentation framework designed to mitigate spurious correlations in machine learning when group labels are unavailable. It uses cluster-derived sub-labels and class labels to fine‑tune a conditional generative model and text encoder, producing synthetic data that fills underrepresented regions and creates a balanced validation set for last‑layer reweighting. Experiments show SAGE improves worst‑group accuracy to 89.5%, 85.7%, and 79.1% on Waterbirds, CelebA, and MetaShift, outperforming existing group‑label‑free baselines by up to 7.7 percentage points.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

fine-tuning

arXiv AI

Oct 2

Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise

arXiv:2610.01028v1 Announce Type: cross Abstract: Machine learning models often suffer performance degradation under subpopulation shift, particularly when spurious correlations cause models to rely...

By Sung Ho Jo, Seonghwi Kim, Wonsang Yun, Minwoo Chae

benchmarks safety

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...

By Hanshu Rao, Guangzeng Han, Xiaolei Huang

llms nlp benchmarks

arXiv AI

Jun 9

Large Language Models for Imbalanced Classification: Diversity makes the difference

arXiv:2510. 09783v2 Announce Type: replace-cross Abstract: Oversampling is one of the most widely used approaches for addressing imbalanced classification.

By Dang Nguyen, Sunil Gupta, Kien Do, Thin Nguyen, Taylor Braund, Alexis Whitton, Svetha Venkatesh

llms fine-tuning benchmarks

arXiv AI

Jul 21

Data Balancing Strategies: A Systematic Survey of Resampling and Augmentation Methods

arXiv:2505. 13518v3 Announce Type: replace-cross Abstract: Imbalanced datasets, where one class significantly outnumbers others, remain a persistent challenge in machine learning, often biasing predictions toward the majority class and degrading classifier performance.

By Behnam Yousefimehr, Mehdi Ghatee, Javad Fazli, Shervin Ghaffari, Zahra Rafei, Mohammad Amin Seifi, Sajed Tavakoli, Abolfazl Nikahd, Mahdi Razi Gandomani, Alireza Orouji, Ramtin Mahmoudi Kashani, Sarina Heshmati, Negin Sadat Mousavi

diffusion efficiency safety

arXiv Machine Learning

Jun 3

Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing

arXiv:2606. 02830v1 Announce Type: new Abstract: Real-world datasets often contain spurious correlations that are not causally related to the target label.

By Arda Fazla, Abolfazl Hashemi

benchmarks

arXiv Machine Learning

Oct 2

Rank-Constrained Adaptation for Reliable Real-World Performance

arXiv:2602.06924v3 Announce Type: replace Abstract: Deep learning models trained to optimize average accuracy often exhibit systematic failures on particular subpopulations. In real-world settings li...

By Abinitha Gourabathina, Hyewon Jeong, Teya Bergamaschi, Marzyeh Ghassemi, Collin Stultz

One email a morning, machine-written

Related stories

Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise

AIA$^{2}$: Attribute-Agnostic Imbalance Augmentation for Subgroup Robustness

Large Language Models for Imbalanced Classification: Diversity makes the difference

Data Balancing Strategies: A Systematic Survey of Resampling and Augmentation Methods

Mitigating Spurious Correlations with Memorization-Guided Dataset De-Biasing

Rank-Constrained Adaptation for Reliable Real-World Performance