DeepProofLog: Efficient Proving in Deep Stochastic Logic Programs
This addresses the scalability problem for users of neurosymbolic AI, enabling more efficient reasoning in complex domains, though it appears incremental as it builds on existing stochastic logic program methods.
The paper tackles the scalability limitations of neurosymbolic AI systems by introducing DeepProofLog, a novel system based on stochastic logic programs that parameterizes derivation steps with neural networks and maps resolution to Markov Decision Processes, enabling efficient inference and learning. Experiments show it outperforms state-of-the-art systems, advancing scalability to larger and more complex settings.
Neurosymbolic (NeSy) AI aims to combine the strengths of neural architectures and symbolic reasoning to improve the accuracy, interpretability, and generalization capability of AI models. While logic inference on top of subsymbolic modules has been shown to effectively guarantee these properties, this often comes at the cost of reduced scalability, which can severely limit the usability of NeSy models. This paper introduces DeepProofLog (DPrL), a novel NeSy system based on stochastic logic programs, which addresses the scalability limitations of previous methods. DPrL parameterizes all derivation steps with neural networks, allowing efficient neural guidance over the proving system. Additionally, we establish a formal mapping between the resolution process of our deep stochastic logic programs and Markov Decision Processes, enabling the application of dynamic programming and reinforcement learning techniques for efficient inference and learning. This theoretical connection improves scalability for complex proof spaces and large knowledge bases. Our experiments on standard NeSy benchmarks and knowledge graph reasoning tasks demonstrate that DPrL outperforms existing state-of-the-art NeSy systems, advancing scalability to larger and more complex settings than previously possible.