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.
By Yiming Luo, Rongqiang Zhao, Jie Liu
arXiv:2606. 14965v1 Announce Type: new Abstract: Synthetic instance-dependent label noise (IDN) benchmarks are widely used to evaluate noisy-label learning methods, yet existing approaches typically generate noise through imperfect annotators or classifier raters, leaving the source of ambiguity implicit.
By Shadman Islam, Agustinus Kristiadi, Mostafa Milani
arXiv:2606. 11699v1 Announce Type: new Abstract: The performance of machine learning and deep learning models largely depends on the quality of the training data.
By Ha-Linh Nguyen, Hong-Anh Nguyen, Minh-Duc La, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo
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
arXiv:2502. 18975v2 Announce Type: replace Abstract: Machine learning models are inherently bound to the distribution of the training data, often exploiting non-causal shortcuts.
By Martin Surner, Abdelmajid Khelil, Ludwig Bothmann
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
arXiv:2608. 03432v1 Announce Type: new Abstract: Refurbishment-based noisy-label learning mixes an observed label with a model-derived pseudo target, typically using one sample-wise cleanliness score to control both branches.
By Wenxiao Fan, Kan Li
FedCC is a new algorithm for distillation-based federated learning that tackles label distribution skew by allowing clients to mark ambiguous samples as 'unknown' instead of forcing a potentially wrong classification. By adding this extra class and calibrating pseudo-labels on a public dataset, FedCC balances confidence across majority and minority classes. Experiments show that FedCC outperforms existing methods, achieving 67.3% accuracy even when each client has data from only one of ten classes, whereas baselines drop to near-random performance.
By Wenxuan Ye, Onur Ayan, Xueli An, Georg Carle
arXiv:2608. 05419v1 Announce Type: cross Abstract: Models trained by empirical risk minimization on data containing spurious correlations achieve high average accuracy while failing on subpopulations where the correlation does not hold.
By Nilesh Kumar
arXiv:2608. 13190v1 Announce Type: new Abstract: Group-robust learning is crucial for maintaining accuracy on rare subpopulations when training-group labels are unavailable.
By Qianqian Wang, Yunshan Li, Dawei Huang, Wenwu Gong, Lili Yang
arXiv:2511. 22823v2 Announce Type: replace-cross Abstract: Weakly supervised learning has emerged as a practical alternative to fully supervised learning when complete and accurate labels are costly or infeasible to acquire.
By Miao Zhang, Junpeng Li, Changchun Hua, Yana Yang
The paper introduces OTROPE, a likelihood‑free method for off‑policy evaluation of large language models (LLMs) that uses optimal transport to align labeled samples from a behavior model with unlabeled samples from a target model in a semantic space. OTROPE corrects human‑labeled residuals with proxy predictors, achieving a doubly robust evaluation without requiring behavior‑policy modeling or density‑ratio estimation. The authors provide theoretical guarantees for consistency and convergence, and demonstrate through synthetic and real LLM tasks that OTROPE outperforms existing baselines and can elevate weaker evaluators to match or exceed stronger ones.
By Liner Xiang, Wenbo Zhang, Hengrui Cai