Independence Is Not an Issue in Neurosymbolic AI
This work addresses a potential misconception in neurosymbolic AI, which could impact researchers and practitioners using these models, though it appears incremental as it refutes an existing claim without introducing new methods.
The paper challenges the claim that conditional independence in neurosymbolic AI causes deterministic bias, arguing instead that the bias arises from improper application of the models.
A popular approach to neurosymbolic AI is to take the output of the last layer of a neural network, e.g. a softmax activation, and pass it through a sparse computation graph encoding certain logical constraints one wishes to enforce. This induces a probability distribution over a set of random variables, which happen to be conditionally independent of each other in many commonly used neurosymbolic AI models. Such conditionally independent random variables have been deemed harmful as their presence has been observed to co-occur with a phenomenon dubbed deterministic bias, where systems learn to deterministically prefer one of the valid solutions from the solution space over the others. We provide evidence contesting this conclusion and show that the phenomenon of deterministic bias is an artifact of improperly applying neurosymbolic AI.