.png){kind=icon}
返回
Quantified neural Markov logic networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ijar.2024.109172.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Markov Logic Networks (MLNs) are discrete generative models in the exponential family. However, specifying these rules requires considerable expertise and can pose a significant challenge. To overcome this limitation, Neural MLNs (NMLNs) have been introduced, enabling the specification of potential functions as neural networks. Thanks to the compact representation of their neural potential functions, NMLNs have shown impressive performance in modeling complex domains like molecular data. Despite the superior performance of NMLNs, their theoretical expressiveness is still equivalent to that of MLNs without quantifiers. In this paper, we propose a new class of NMLN, called Quantified NMLN, that extends the expressivity of NMLNs to the quantified setting. Furthermore, we demonstrate how to leverage the neural nature of NMLNs to employ learnable aggregation functions as quantifiers, increasing expressivity even further. We demonstrate the competitiveness of Quantified NMLNs over original NMLNs and state-of-the-art diffusion models in molecule generation experiments.
Keyword:
Markov logic networks
Statistical relational learning
期刊
IF:
3
论文数:
3.0K
被引数:
5.1K
机构
引用论文
分享收藏分享收藏Real-time and offline techniques for identifying obstructive sleep apnea patients用于识别阻塞性睡眠呼吸暂停患者的实时和离线技术
PREAI
分享收藏ChEMBL: towards direct deposition of bioassay dataChEMBL: 走向生物测定数据的直接沉积.png)
NUCLEIC ACIDS RESEARCH
OAAI
NUCLEIC ACIDS RESEARCHIF13.1
OAAI分享收藏Cross-linkable Polymer Matrix for Enhanced Thermal Stability of Succinonitrile-based Polymer Electrolyte in Lithium Rechargeable Batteries可交联聚合物基质，用于增强锂可充电电池中基于丁二腈的聚合物电解质的热稳定性
OAAI
OAAI分享收藏
查看更多内容