Neuro-Symbolic Forward Reasoning
This addresses the challenge of enabling AI systems to perform logical reasoning from raw inputs, which is incremental as it builds on existing neuro-symbolic AI methods.
The paper tackles the problem of integrating reasoning with deep learning by proposing the Neuro-Symbolic Forward Reasoner (NSFR), which combines differentiable forward-chaining using first-order logic with object-centric learning, and demonstrates its effectiveness on object-centric reasoning datasets like 2D Kandinsky patterns and 3D CLEVR-Hans.
Reasoning is an essential part of human intelligence and thus has been a long-standing goal in artificial intelligence research. With the recent success of deep learning, incorporating reasoning with deep learning systems, i.e., neuro-symbolic AI has become a major field of interest. We propose the Neuro-Symbolic Forward Reasoner (NSFR), a new approach for reasoning tasks taking advantage of differentiable forward-chaining using first-order logic. The key idea is to combine differentiable forward-chaining reasoning with object-centric (deep) learning. Differentiable forward-chaining reasoning computes logical entailments smoothly, i.e., it deduces new facts from given facts and rules in a differentiable manner. The object-centric learning approach factorizes raw inputs into representations in terms of objects. Thus, it allows us to provide a consistent framework to perform the forward-chaining inference from raw inputs. NSFR factorizes the raw inputs into the object-centric representations, converts them into probabilistic ground atoms, and finally performs differentiable forward-chaining inference using weighted rules for inference. Our comprehensive experimental evaluations on object-centric reasoning data sets, 2D Kandinsky patterns and 3D CLEVR-Hans, and a variety of tasks show the effectiveness and advantage of our approach.