A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference

Emile van Krieken, Thiviyan Thanapalasingam, Jakub M. Tomczak, Frank Van Harmelen, Annette Ten Teije

Keywords: Neurosymbolic Learning, Generative Modeling, Approximate Inference

TL;DR: We scale deep learning models that use symbolic reasoning using a neural network that performs approximate inference

Abstract: 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.

Submission Number: 4610