Representation Invariance and Allocation: When Subgroup Balance Matters
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Addressing Missing Sources with Adversarial Support-Matching
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 …
FairnessIs Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning
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 LearningRetrievalOn the Sample Complexity of Learning under Invariance and Geometric Stability
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…
validFairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization
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 LearningOn the Sample Complexity of Learning under Geometric Stability
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