paper-with-me

홈 › Papers

Representation Invariance and Allocation: When Subgroup Balance Matters

2025-12-10 · Anissa Alloula, Charles Jones, Zuzanna Wakefield-Skorniewska, Francesco Quinzan, Bartłomiej Papież arxiv

Unequal representation of demographic groups in training data poses challenges to model generalisation across populations. Standard practice assumes that balancing subgroup representation optimises performance. However, recent empirical results contradict this assumption: in some cases, imbalanced data distributions actually improve subgroup performance, while in others, subgroup performance remains unaffected by the absence of an entire subgroup during training. We conduct a systematic study of subgroup allocation across four vision and language models, varying training data composition to characterise the sensitivity of subgroup performance to data balance. We propose the latent separation hypothesis, which states that a partially fine-tuned model's dependence on subgroup representation is determined by the degree of separation between subgroups in the latent space of the pre-trained model. We formalise this hypothesis, provide theoretical analysis, and validate it empirically. Finally, we present a practical application to foundation model fine-tuning, demonstrating that quantitative analysis of latent subgroup separation can inform data collection and balancing decisions.

📄 PDF Abstract BibTeX arXiv:2512.09496

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Addressing Missing Sources with Adversarial Support-Matching

2022-03-24 · Thomas Kehrenberg, Myles Bartlett, Viktoriia Sharmanska, Novi Quadrianto

When trained on diverse labeled data, machine learning models have proven themselves to be a powerful tool in all facets of society. However, due to budget limitations, deliberate or non-deliberate censorship, and other …

Fairness

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

2022-03-23 · ICLR 2022 4 · Natalie Dullerud, Karsten Roth, Kimia Hamidieh, Nicolas Papernot 외

Deep metric learning (DML) enables learning with less supervision through its emphasis on the similarity structure of representations. There has been much work on improving generalization of DML in settings like zero-sho…

AttributeFairnessMetric LearningRetrieval

On the Sample Complexity of Learning under Invariance and Geometric Stability

2021-06-14 · Alberto Bietti, Luca Venturi, Joan Bruna

Many supervised learning problems involve high-dimensional data such as images, text, or graphs. In order to make efficient use of data, it is often useful to leverage certain geometric priors in the problem at hand, suc…

valid

Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization

2026-08-24 · Sunhee Hwang arxiv

Deep learning models often produce performance disparities across demographic groups, due to the training data imbalance with respect to sensitive attributes such as gender or age. To address this problem, existing work …

Representation Learning

On the Sample Complexity of Learning under Geometric Stability

2021-12-01 · NeurIPS 2021 12 · Alberto Bietti, Luca Venturi, Joan Bruna

Many supervised learning problems involve high-dimensional data such as images, text, or graphs. In order to make efficient use of data, it is often useful to leverage certain geometric priors in the problem at hand, suc…

valid