Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models

2026-07-09

AI Summary

This work addresses the challenge of integrating symbolic reasoning with neural learning in dynamic perception and interaction scenarios by proposing the first end-to-end trainable neuro-symbolic framework centered on Answer Set Programming (ASP). The approach modularly combines ASP with energy-based models to jointly optimize logical constraints, background knowledge, and non-monotonic reasoning within a continuous latent space. It further extends the integration paradigm of ASP with probabilistic logic and modal theory answer sets. Experimental validation on MNIST, CLEVR visual question answering, and MOT multi-object tracking benchmarks demonstrates the framework’s effectiveness, highlighting its practicality and robustness in dynamic environments.

Abstract

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.

Problem

• Answer Set Programming
• Neurosymbolic Reasoning
• Energy Based Models
• End-to-End Learning
• Non-monotonic Inference

Innovation

• Answer Set Programming
• Energy-Based Models
• Neurosymbolic Reasoning
• End-to-End Learning
• Non-monotonic Inference