Author:
Islam Mohammad Maminur,Sarkhel Somdeb,Venugopal Deepak
Abstract
We present a dense representation for Markov Logic Networks (MLNs) called Obj2Vec that encodes symmetries in the MLN structure. Identifying symmetries is a key challenge for lifted inference algorithms and we leverage advances in neural networks to learn symmetries which are hard to specify using hand-crafted features. Specifically, we learn an embedding for MLN objects that predicts the context of an object, i.e., objects that appear along with it in formulas of the MLN, since common contexts indicate symmetry in the distribution. Importantly, our formulation leverages well-known skip-gram models that allow us to learn the embedding efficiently. Finally, to reduce the size of the ground MLN, we sample objects based on their learned embeddings. We integrate Obj2Vec with several inference algorithms, and show the scalability and accuracy of our approach compared to other state-of-the-art methods.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Interpretable Explanations for Probabilistic Inference in Markov Logic;2021 IEEE International Conference on Big Data (Big Data);2021-12-15
2. Contrastive Learning in Neural Tensor Networks using Asymmetric Examples;2021 IEEE International Conference on Big Data (Big Data);2021-12-15