arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.11367cs.AIcs.LG
收藏

迈向具有神经符号推理与松弛的概率归纳逻辑编程

Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation

TNO(荷兰应用科学研究组织)

Fieke Hillerstrom, Gertjan Burghouts

AI总结:

针对传统ILP无法处理概率背景知识的问题,提出Propper框架,结合神经符号推理、连续假设选择标准(BCE)和约束松弛(NoisyCombo),能从极少示例中学习并优于现有模型。

摘要:

许多归纳逻辑编程(ILP)方法无法从概率背景知识中学习程序,例如来自感知数据或带有概率的神经网络的数据。我们提出了Propper,它通过将ILP与神经符号推理、假设选择的连续标准(BCE)以及假设约束器的松弛(NoisyCombo)相结合,来处理有缺陷和概率性的背景知识。对于噪声图像中的关系模式,Propper能从仅8个示例中学习程序。它优于二值ILP和统计模型(如图神经网络)。

英文摘要:

Many inductive logic programming (ILP) methods are incapable of learning programs from probabilistic background knowledge, e.g. coming from sensory data or neural networks with probabilities. We propose Propper, which handles flawed and probabilistic background knowledge by extending ILP with a combination of neurosymbolic inference, a continuous criterion for hypothesis selection (BCE) and a relaxation of the hypothesis constrainer (NoisyCombo). For relational patterns in noisy images, Propper can learn programs from as few as 8 examples. It outperforms binary ILP and statistical models such as a Graph Neural Network.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑