Metraipolis › archive › dc_35ae6cedf6e4
AIA$^{2}$: Attribute-Agnostic Imbalance Augmentation for Subgroup Robustness — arXiv:2608.30297
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30297
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:07:26.995Z
- SHA-256 of the archived text
bc8baf343681c3c07142ab66add0ba33c6c559d19a3acfc44129fa65c73f1b94- Stable URL of this page
https://metraipolis.com/documento/dc_35ae6cedf6e4
How to cite
AIA$^{2}$: Attribute-Agnostic Imbalance Augmentation for Subgroup Robustness — arXiv:2608.30297 — arXiv (en), https://arxiv.org/abs/2608.30297 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35ae6cedf6e4 (Metraipolis archive dc_35ae6cedf6e4, sha256 bc8baf343681c3c07142ab66add0ba33c6c559d19a3acfc44129fa65c73f1b94)
BibTeX
@misc{dc35ae6cedf6e4,
title = {AIA$^2$: Attribute-Agnostic Imbalance Augmentation for Subgroup Robustness — arXiv:2608.30297},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30297},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35ae6cedf6e4; sha256 bc8baf343681c3c07142ab66add0ba33c6c559d19a3acfc44129fa65c73f1b94},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30297. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Attributes describing data content and context can induce diverse imbalance patterns that go beyond label imbalance alone. However, existing studies primarily address label imbalance while overlooking data attributes, such as topics and demographics, which can induce meaningful subgroup structure while causing model degradation on underrepresented subgroups. We propose Attribute-Agnostic Imbalance Augmentation (AIA$^{2}$), a framework for improving model robustness under varying subgroup imbalances without explicit subgroup annotations. AIA$^{2}$ automatically discovers varying imbalances via latent semantic distributions, obtains slices with both learning difficulty and subgroup imbalance deficits, and deploys a large language model (LLM) for subgroup-aware imbalance augmentation. We have evaluated AIA$^{2}$ on 5 popular corpora with rich domains and their attribute values, covering social issues and diverse topics. Results show improved performance on the lowest-performing subgroups and consistent gains over competitive baselines. Ablation studies confirm complementary contributions from each component, and additional analyses show that AIA$^{2}$ provides a practical and consistent way to improve worst-group robustness under data subgroup imbalance. Code is available at this https URL .
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.30297 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T07:47:52.793Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).