AI models often rely on "spurious correlations," making decisions based on unimportant and potentially misleading information. Researchers have now discovered these learned spurious correlations can ...

Self-supervised learning (SSL) approaches have recently become state-of-the-art (SOTA) for personalized recommendation. The core idea of SSL in recommendation is to learn better user and item ...

In many instances—including areas examined by the researchers such as chest X-rays, cancer histopathology images, and hate speech detection—such spurious correlations are much harder to detect.