SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming
This work addresses the challenge of creating a unified neuro-symbolic framework for AI researchers, though it appears incremental as it builds on existing concepts like probabilistic circuits and answer set programming.
The authors tackled the problem of integrating neural networks and symbolic methods in AI by introducing SLASH, a deep probabilistic programming language that unifies neural and symbolic components via answer set programming, achieving state-of-the-art performance on tasks like MNIST addition and missing data prediction.
The goal of combining the robustness of neural networks and the expressivity of symbolic methods has rekindled the interest in neuro-symbolic AI. Recent advancements in neuro-symbolic AI often consider specifically-tailored architectures consisting of disjoint neural and symbolic components, and thus do not exhibit desired gains that can be achieved by integrating them into a unifying framework. We introduce SLASH -- a novel deep probabilistic programming language (DPPL). At its core, SLASH consists of Neural-Probabilistic Predicates (NPPs) and logical programs which are united via answer set programming. The probability estimates resulting from NPPs act as the binding element between the logical program and raw input data, thereby allowing SLASH to answer task-dependent logical queries. This allows SLASH to elegantly integrate the symbolic and neural components in a unified framework. We evaluate SLASH on the benchmark data of MNIST addition as well as novel tasks for DPPLs such as missing data prediction and set prediction with state-of-the-art performance, thereby showing the effectiveness and generality of our method.