Independence Is Not an Issue in Neurosymbolic AI
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.
Code (0)
등록된 구현이 없습니다.
Tasks
validMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Neurosymbolic Diffusion Models
Neurosymbolic (NeSy) predictors combine neural perception with symbolic reasoning to solve tasks like visual reasoning. However, standard NeSy predictors assume conditional independence between the symbols they extract, …
Autonomous DrivingUncertainty QuantificationVisual ReasoningNeurosymbolic Reasoning Shortcuts under the Independence Assumption
The ubiquitous independence assumption among symbolic concepts in neurosymbolic (NeSy) predictors is a convenient simplification: NeSy predictors use it to speed up probabilistic reasoning. Recent works like van Krieken …
On the Independence Assumption in Neurosymbolic Learning
State-of-the-art neurosymbolic learning systems use probabilistic reasoning to guide neural networks towards predictions that conform to logical constraints over symbols. Many such systems assume that the probabilities o…
Uncertainty QuantificationvalidIID Relaxation by Logical Expressivity: A Research Agenda for Fitting Logics to Neurosymbolic Requirements
Neurosymbolic background knowledge and the expressivity required of its logic can break Machine Learning assumptions about data Independence and Identical Distribution. In this position paper we propose to analyze IID re…
PositionParallel Neurosymbolic Integration with Concordia
Parallel neurosymbolic architectures have been applied effectively in NLP by distilling knowledge from a logic theory into a deep model.However, prior art faces several limitations including supporting restricted forms o…
Action DetectionActivity DetectionEntity Linking