Publikation
Answer Set Networks: Casting Answer Set Programming into Deep Learning
Arseny Skryagin; Daniel Ochs; Phillip Deibert; Simon Kohaut; Devendra Singh Dhami; Kristian Kersting
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2412.14814, Pages 1-16, arXiv, 2024.
Zusammenfassung
Although Answer Set Programming (ASP) allows constrain-
ing neural-symbolic (NeSy) systems, its employment is hin-
dered by the prohibitive costs of computing stable mod-
els and the CPU-bound nature of state-of-the-art solvers. To
this end, we propose Answer Set Networks (ASN), a NeSy
solver. Based on Graph Neural Networks (GNN), ASNs are
a scalable approach to ASP-based Deep Probabilistic Logic
Programming (DPPL). Specifically, we show how to trans-
late ASPs into ASNs and demonstrate how ASNs can ef-
ficiently solve the encoded problem by leveraging GPU’s
batching and parallelization capabilities. Our experimental
evaluations demonstrate that ASNs outperform state-of-the-
art CPU-bound NeSy systems on multiple tasks. Simultane-
ously, we make the following two contributions based on the
strengths of ASNs. Namely, we are the first to show the fine-
tuning of Large Language Models (LLM) with DPPLs, em-
ploying ASNs to guide the training with logic. Further, we
show the “constitutional navigation” of drones, i.e., encoding
public aviation laws in an ASN for routing Unmanned Aerial
Vehicles in uncertain environments.