Evidential Alignment improves worst-group accuracy by upweighting a biased model's high-uncertainty errors and retraining the last layer with a calibration set, without group annotations.
Learning Robust Classifiers with Self-Guided Spurious Correlation Mitigation
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious correlations typically relies on annotations of spurious correlations in data, which are often expensive to get. In this paper, we tackle an annotation-free setting and propose a self-guided spurious correlation mitigation framework. Our framework automatically constructs fine-grained training labels tailored for a classifier obtained with empirical risk minimization to improve its robustness against spurious correlations. The fine-grained training labels are formulated with different prediction behaviors of the classifier identified in a novel spuriousness embedding space. We construct the space with automatically detected conceptual attributes and a novel spuriousness metric which measures how likely a class-attribute correlation is exploited for predictions. We demonstrate that training the classifier to distinguish different prediction behaviors reduces its reliance on spurious correlations without knowing them a priori and outperforms prior methods on five real-world datasets.
citation-role summary
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Improving Group Robustness on Spurious Correlation via Evidential Alignment
Evidential Alignment improves worst-group accuracy by upweighting a biased model's high-uncertainty errors and retraining the last layer with a calibration set, without group annotations.