Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models
This work advances neurosymbolic AI by providing a modular, ASP-based framework for robust reasoning in dynamic domains, though it is an incremental improvement over existing probabilistic and ASP-based approaches.
The paper presents a neurosymbolic reasoning and learning method integrating answer set programming with energy-based models, enabling end-to-end training with background knowledge and non-monotonic inference. It achieves competitive results on Clevr and MOT benchmarks.
We present a general neurosymbolic reasoning and learning methodology based on a modular integration of answer set programming with an energy based model substrate. Key contributions are: (1) supporting joint optimisation in the continuous latent space through explicit ASP-based declarative semantics fully incorporating background knowledge, constraints, non-monotonic inference; and (2) advancing recent works at the interface of answer sets, probabilistic logic, and answer set modulo theories by providing a generalised model and practical platform for ASP-centric robust, end-to-end training for applications in dynamic domains (e.g., involving perception and interaction). We provide a practical implementation, and demonstrate basic use and application (with MNIST), and evaluate with the visual question-answering benchmark Clevr and the multi-object tracking benchmark MOT.