10 citations · 17 across the 3 of their papers we have counts for
3 papers
Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers
Wanqian Yang, Polina Kirichenko, Micah Goldblum +1
Deep neural networks are susceptible to shortcut learning, using simple features to achieve low training loss without discovering essential semantic structure. Contrary to prior be…
Incorporating Interpretable Output Constraints in Bayesian Neural Networks
Wanqian Yang, Lars Lorch, Moritz A. Graule +2
Domains where supervised models are deployed often come with task-specific constraints, such as prior expert knowledge on the ground-truth function, or desiderata like safety and f…
Output-Constrained Bayesian Neural Networks
Wanqian Yang, Lars Lorch, Moritz A. Graule +5
Bayesian neural network (BNN) priors are defined in parameter space, making it hard to encode prior knowledge expressed in function space. We formulate a prior that incorporates fu…