Parallel Neurosymbolic Integration with Concordia
This work addresses the problem of integrating logic and neural networks more flexibly for researchers and practitioners in AI, though it appears incremental as it builds on existing neurosymbolic methods.
The authors tackled the limitations of prior parallel neurosymbolic architectures, such as restricted logic forms and independence assumptions, by introducing Concordia, a framework that is agnostic to the deep network and logic theory, supporting a wide range of probabilistic theories and improving accuracy on tasks like collective activity detection, entity linking, and recommendation.
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 of logic theories and relying on the assumption of independence between the logic and the deep network. We present Concordia, a framework overcoming the limitations of prior art. Concordia is agnostic both to the deep network and the logic theory offering support for a wide range of probabilistic theories. Our framework can support supervised training of both components and unsupervised training of the neural component. Concordia has been successfully applied to tasks beyond NLP and data classification, improving the accuracy of state-of-the-art on collective activity detection, entity linking and recommendation tasks.