B1430
Title: Transfer learning with spurious correlations
Authors: Linjun Zhang - Rutgers University (United States) [presenting]
Abstract: Machine learning algorithms often rely on spurious correlations to make predictions, which hinders generalization beyond training environments. For instance, models that associate cats with bed backgrounds can fail to predict the existence of cats in other environments without beds. Mitigating spurious correlations is crucial in building trustworthy models. However, the existing works lack transparency to offer insights into the mitigation process. A framework is provided to conduct statistical analysis with spurious correlation. Additionally, theoretical analysis is offered and it is guaranteed to understand the benefits of models trained by the proposed method.
