paper-with-me

홈 › Papers

Towards Last-layer Retraining for Group Robustness with Fewer Annotations

2023-09-15 · NeurIPS 2023 11 · Tyler LaBonte, Vidya Muthukumar, Abhishek Kumar

Empirical risk minimization (ERM) of neural networks is prone to over-reliance on spurious correlations and poor generalization on minority groups. The recent deep feature reweighting (DFR) technique achieves state-of-the-art group robustness via simple last-layer retraining, but it requires held-out group and class annotations to construct a group-balanced reweighting dataset. In this work, we examine this impractical requirement and find that last-layer retraining can be surprisingly effective with no group annotations (other than for model selection) and only a handful of class annotations. We first show that last-layer retraining can greatly improve worst-group accuracy even when the reweighting dataset has only a small proportion of worst-group data. This implies a "free lunch" where holding out a subset of training data to retrain the last layer can substantially outperform ERM on the entire dataset with no additional data or annotations. To further improve group robustness, we introduce a lightweight method called selective last-layer finetuning (SELF), which constructs the reweighting dataset using misclassifications or disagreements. Our empirical and theoretical results present the first evidence that model disagreement upsamples worst-group data, enabling SELF to nearly match DFR on four well-established benchmarks across vision and language tasks with no group annotations and less than 3% of the held-out class annotations. Our code is available at https://github.com/tmlabonte/last-layer-retraining.

📄 PDF Abstract BibTeX arXiv:2309.08534

Code (1)

tmlabonte/last-layer-retraining 공식 구현 pytorch

Tasks

Model Selection

Similar Papers 제목 키워드 기반

On the Unreasonable Effectiveness of Last-layer Retraining

2025-12-01 · John C. Hill, Tyler LaBonte, Xinchen Zhang, Vidya Muthukumar arxiv

Last-layer retraining (LLR) methods -- wherein the last layer of a neural network is reinitialized and retrained on a held-out set following ERM training -- have garnered interest as an efficient approach to rectify depe…

Label Noise Robustness for Domain-Agnostic Fair Corrections via Nearest Neighbors Label Spreading

2024-06-13 · Nathan Stromberg, Rohan Ayyagari, Sanmi Koyejo, Richard Nock 외

Last-layer retraining methods have emerged as an efficient framework for correcting existing base models. Within this framework, several methods have been proposed to deal with correcting models for subgroup fairness wit…

Fairness

Theoretical Guarantees of Data Augmented Last Layer Retraining Methods

2024-05-09 · Monica Welfert, Nathan Stromberg, Lalitha Sankar

Ensuring fair predictions across many distinct subpopulations in the training data can be prohibitive for large models. Recently, simple linear last layer retraining strategies, in combination with data augmentation meth…

Data Augmentation

Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations?

2023-08-01 · Phuong Quynh Le, Jörg Schlötterer, Christin Seifert

Models trained with empirical risk minimization (ERM) are known to learn to rely on spurious features, i.e., their prediction is based on undesired auxiliary features which are strongly correlated with class labels but l…

TLDR: Text Based Last-layer Retraining for Debiasing Image Classifiers

2023-11-30 · Juhyeon Park, Seokhyeon Jeong, Taesup Moon

An image classifier may depend on incidental features stemming from a strong correlation between the feature and the classification target in the training dataset. Recently, Last Layer Retraining (LLR) with group-balance…