This technology is a machine learning approach for imputing observations across different observational environments, which can be used to enhance models’ performance on data that falls outside the distribution of the training data.
Artificial intelligence (AI) and machine learning (ML) models tend to learn spurious correlations between concepts of interest and the context in which relevant examples tend to be observable, i.e. their observational environments. Therefore, models perform worse when evaluated on data that contradicts these correlations. Despite the importance of models’ ability to generalize to observations made in different environments and contexts, designing test datasets to evaluate model generalizability has remained difficult, and current existing methods for mitigating confounding by spurious correlations have been ineffective in yielding models that generalize to out-of-distribution (OOD) data.
This technology presents an approach, termed Interventional Style Transfer (IST), to diminish the confounding effects of observational environments on feature learning during machine learning model training. It uses a generative model to faithfully impute observations as if they had been collected in different observational environments. In the yielded interventional training distribution, observations thus effectively exist in every observational environment, removing spurious correlations between them and relevant concepts of interest. To evaluate OOD generalization in models, hierarchies within the causal data generation process can be leveraged to establish increasingly challenging OOD generalization tasks. When trained on IST training distributions, computer vision models exhibited major improvements in learning causal representations across these OOD generalization tasks.
This technology has been validated with single-cell fluorescent microscopy datasets.
Patent Pending (US20260087786) (WO/2024/249579)
IR CU23355
Licensing Contact: Kristin Neuman
