Answer Set Networks: Casting Answer Set Programming into Deep Learning
This addresses the bottleneck of ASP in neural-symbolic AI for researchers and practitioners, enabling applications like LLM finetuning and drone navigation, though it is incremental as it adapts existing methods to a new context.
The authors tackled the prohibitive computational costs of Answer Set Programming (ASP) in neural-symbolic systems by proposing Answer Set Networks (ASN), a scalable approach based on Graph Neural Networks that leverages GPU capabilities, resulting in outperforming state-of-the-art CPU-bound systems on multiple tasks.
Although Answer Set Programming (ASP) allows constraining neural-symbolic (NeSy) systems, its employment is hindered by the prohibitive costs of computing stable models 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 translate ASPs into ASNs and demonstrate how ASNs can efficiently 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. Simultaneously, we make the following two contributions based on the strengths of ASNs. Namely, we are the first to show the finetuning of Large Language Models (LLM) with DPPLs, employing 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.