Learning Mixtures of MLNs
Learning Mixtures of MLNs
复制标题
MLN 的学习混合
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
D. Venugopal
中科院分区：
文献类型：
--
作者：
Mohammad Maminur Islam;Somdeb Sarkhel;D. Venugopal
在马尔可夫逻辑网络（mln）中，权重学习是一个具有挑战性的问题，因为作为mln一阶表示基础的基本命题概率图模型的规模很大。虽然已经提出了使用提升推理的更复杂的权重学习方法，但这些方法通常只能在缺乏证据的情况下扩大规模，即在生成权重学习中。在判别学习中，证据通常会破坏对称性，现有的方法缺乏可扩展性。在本文中，我们提出了一种新的、直观的方法，利用近似对称性来判别学习mln。具体来说，我们通过将近似对称的原子聚在一起并从每个聚类中选择一个具有代表性的原子来减小训练数据库的大小。然而，从聚类中做出的每个选择都会导致不同的分布，这增加了我们学习模型的不确定性。为了减少这种不确定性，我们通过叠加不同的分布来学习有限混合模型，其中模型的参数是使用EM方法学习的。我们在几个基准测试上的结果表明，与现有的最先进的MLN学习方法相比，我们的方法更具可扩展性和准确性。
Weight learning is a challenging problem in Markov Logic Networks (MLNs) due to the large size of the ground propositional probabilistic graphical model that underlies the first-order representation of MLNs. Though more sophisticated weight learning methods that use lifted inference have been proposed, such methods can typically scale up only in the absence of evidence, namely in generative weight learning. In discriminative learning, where the evidence typically destroys symmetries, existing approaches are lacking in scalability. In this paper, we propose a novel, intuitive approach for learning MLNs discriminatively by utilizing approximate symmetries. Specifically, we reduce the size of the training database by clustering approximately symmetric atoms together and selecting a representative atom from each cluster. However, each choice made from the clusters induces a different distribution, increasing the uncertainty in our learned model. To reduce this uncertainty, we learn a finite mixture model by stacking the different distributions, where the parameters of the model are learned using an EM approach. Our results on several benchmarks show that our approach is much more scalable and accurate as compared to existing state-of-the-art MLN learning methods.