发表机构
Czech Technical University; KU Leuven（捷克技术大学; 鲁汶大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对神经马尔可夫逻辑网络在大结构上表现欠佳的问题，通过用图神经网络增强势函数表达能力，结合受并行回火启发的并行噪声训练和推理算法，提升其在图生成及小分子结构生成中的性能。
AI 中文摘要
神经马尔可夫逻辑网络（NMLNs）是一种灵活的神经符号关系模型。先前研究表明，NMLNs作为小关系结构的生成模型性能较强，但在大结构上不如基于扩散的生成图模型。本文从两方面强化NMLNs：一是用图神经网络提高势函数表达能力；二是开发受并行回火马尔可夫链蒙特卡罗方法启发的并行噪声训练和推理算法。这些改进使NMLNs在图生成中相对于基于扩散的生成图模型表现出色，在生成小分子结构时能与基于文本的循环模型性能相当。
英文摘要
Neural Markov Logic Networks (NMLNs) are a flexible neurosymbolic relational model. Previous work has shown that, although NMLNs achieve strong performance as generative models for small relational structures, they underperform diffusion-based generative graph models on larger structures. In this paper, we strengthen NMLNs along two main dimensions: (i) we increase the expressive capacity of their potential functions using graph neural networks, and (ii) we develop a new training and inference algorithm inspired by parallel-tempering Markov chain Monte Carlo methods, which we name parallel noising. Together, these enhancements enable NMLNs to attain strong performance in graph generation relative to general diffusion-based generative graph models. Furthermore, they allow NMLNs to match the performance of specialized text-based recurrent models when generating small molecular structures.
