Spurious correlations can cause model performance to degrade in new environments. Prior causality-inspired work aim to learn invariant representations (e.g., IRM) but typically underperform empirical risk minimization (ERM). Recent alternatives …
Blending visual and textual concepts into a new visual concept is a unique and powerful trait of human beings that can fuel creativity. However, in practice, crossmodal conceptual blending for humans is prone to cognitive biases, like design …
Answering counterfactual queries has important applications such as explainability, robustness, and fairness but is challenging when the causal variables are unobserved and the observations are non-linear mixtures of these latent variables, such as …
While prior federated learning (FL) methods mainly consider client heterogeneity, we focus on the Federated Domain Generalization (DG) task, which introduces train-test heterogeneity in the FL context. Existing evaluations in this field are limited …
A distribution shift can have fundamental consequences such as signaling a change in the operating environment or significantly reducing the accuracy of downstream models. Thus, understanding distribution shifts is critical for examining and …
Shapley values have become one of the most popular feature attribution explanation methods. However, most prior work has focused on post-hoc Shapley explanations, which can be computationally demanding (exponential time complexity) and preclude model …