A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference
This addresses the scalability bottleneck for researchers and practitioners in neurosymbolic AI, particularly in safety-critical applications, though it is an incremental improvement over existing methods like DeepProbLog.
The paper tackles the scalability problem in Probabilistic Neurosymbolic Learning (PNL) by introducing A-NeSI, a framework that performs approximate inference in polynomial time, enabling it to solve three neurosymbolic tasks with exponential combinatorial scaling without performance penalties.
We study the problem of combining neural networks with symbolic reasoning. Recently introduced frameworks for Probabilistic Neurosymbolic Learning (PNL), such as DeepProbLog, perform exponential-time exact inference, limiting the scalability of PNL solutions. We introduce Approximate Neurosymbolic Inference (A-NeSI): a new framework for PNL that uses neural networks for scalable approximate inference. A-NeSI 1) performs approximate inference in polynomial time without changing the semantics of probabilistic logics; 2) is trained using data generated by the background knowledge; 3) can generate symbolic explanations of predictions; and 4) can guarantee the satisfaction of logical constraints at test time, which is vital in safety-critical applications. Our experiments show that A-NeSI is the first end-to-end method to solve three neurosymbolic tasks with exponential combinatorial scaling. Finally, our experiments show that A-NeSI achieves explainability and safety without a penalty in performance.