In-Person Poster presentation / poster accept

Softened Symbol Grounding for Neuro-symbolic Systems

Zenan Li · Yuan Yao · Taolue Chen · Jingwei Xu · Chun Cao · Xiaoxing Ma · Jian Lu

MH1-2-3-4 #46

Keywords: [ Deep Learning and representational learning ] [ Neuro-Symbolic Learning ] [ symbol grounding problem ] [ projection-based sampling ]


Neuro-symbolic learning generally consists of two separated worlds, i.e., neural network training and symbolic constraint solving, whose success hinges on symbol grounding, a fundamental problem in AI. This paper presents a novel, softened symbol grounding process, bridging the gap between the two worlds, and resulting in an effective and efficient neuro-symbolic learning framework. Technically, the framework features (1) modeling of symbol solution states as a Boltzmann distribution, which avoids expensive state searching and facilitates mutually beneficial interactions between network training and symbolic reasoning; (2) a new MCMC technique leveraging projection and SMT solvers, which efficiently samples from disconnected symbol solution spaces; (3) an annealing mechanism that can escape from sub-optimal symbol groundings. Experiments with three representative neuro-symbolic learning tasks demonstrate that, owing to its superior symbol grounding capability, our framework successfully solves problems well beyond the frontier of the existing proposals.

Chat is not available.